From a6105a3f51e25d06d97cb540d33c028315ac9d39 Mon Sep 17 00:00:00 2001 From: Prohurtz <48768484+RedHawk989@users.noreply.github.com> Date: Tue, 31 Jan 2023 12:02:25 -0800 Subject: [PATCH] Revert "Cleaning+SafeCrop" --- EyeTrackApp/eye_processor.py | 304 ++++--- EyeTrackApp/haar_surround_feature.py | 580 ++++++++------ EyeTrackApp/hsrac.py | 1110 +++++++++++++++++++++----- EyeTrackApp/img_utils.py | 12 - EyeTrackApp/ransac.py | 2 +- EyeTrackApp/time_utils.py | 171 ---- EyeTrackApp/utils.py | 2 - 7 files changed, 1387 insertions(+), 794 deletions(-) delete mode 100644 EyeTrackApp/img_utils.py delete mode 100644 EyeTrackApp/time_utils.py delete mode 100644 EyeTrackApp/utils.py diff --git a/EyeTrackApp/eye_processor.py b/EyeTrackApp/eye_processor.py index c7d8903..ac6cef5 100644 --- a/EyeTrackApp/eye_processor.py +++ b/EyeTrackApp/eye_processor.py @@ -1,4 +1,4 @@ -""" +''' ------------------------------------------------------------------------------------------------------ ,@@@@@@ @@ -19,8 +19,8 @@ @@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@( -HSR By: PallasNeko (Optimization Wizard, Contributor), Summer#2406 (Main Algorithm Engineer) -RANSAC 3D By: Summer#2406 (Main Algorithm Engineer), Pupil Labs (pye3d), PallasNeko (Optimization) +HSR By: Sean.Denka (Optimization Wizard, Contributor), Summer#2406 (Main Algorithm Engineer) +RANSAC 3D By: Summer#2406 (Main Algorithm Engineer), Pupil Labs (pye3d), Sean.Denka (Optimization) BLOB By: Prohurtz#0001 (Main App Developer) Algorithm App Implimentations By: Prohurtz#0001, qdot (Inital App Creator) @@ -28,7 +28,7 @@ Additional Contributors: [Assassin], Summer404NotFound, lorow, ZanzyTHEbar Copyright (c) 2022 EyeTrackVR <3 ------------------------------------------------------------------------------------------------------ -""" +''' from operator import truth from dataclasses import dataclass @@ -46,20 +46,19 @@ import numpy as np import cv2 from enum import Enum from one_euro_filter import OneEuroFilter - if sys.platform.startswith("win"): from winsound import PlaySound, SND_FILENAME, SND_ASYNC import importlib from osc_calibrate_filter import * -from haar_surround_feature import External_Run_HSF +from haar_surround_feature import * from blob import * from ransac import * -from hsrac import External_Run_HSRACS +from hsrac import * from blink import * -from intensity_eye_open import * +from intensity_eye_open import * class InformationOrigin(Enum): RANSAC = 1 @@ -68,10 +67,7 @@ class InformationOrigin(Enum): HSF = 4 HSRAC = 5 - bbb = 0 - - @dataclass class EyeInformation: info_type: InformationOrigin @@ -89,7 +85,7 @@ def run_once(f): if not wrapper.has_run: wrapper.has_run = True return f(*args, **kwargs) - + wrapper.has_run = False return wrapper @@ -98,35 +94,36 @@ async def delayed_setting_change(setting, value): await asyncio.sleep(5) setting = value if sys.platform.startswith("win"): - PlaySound("Audio/compleated.wav", SND_FILENAME | SND_ASYNC) + PlaySound('Audio/compleated.wav', SND_FILENAME | SND_ASYNC) + class EyeProcessor: def __init__( - self, - config: "EyeTrackCameraConfig", - settings: "EyeTrackSettingsConfig", - cancellation_event: "threading.Event", - capture_event: "threading.Event", - capture_queue_incoming: "queue.Queue", - image_queue_outgoing: "queue.Queue", - eye_id, + self, + config: "EyeTrackCameraConfig", + settings: "EyeTrackSettingsConfig", + cancellation_event: "threading.Event", + capture_event: "threading.Event", + capture_queue_incoming: "queue.Queue", + image_queue_outgoing: "queue.Queue", + eye_id, ): self.config = config self.settings = settings - + # Cross-thread communication management self.capture_queue_incoming = capture_queue_incoming self.image_queue_outgoing = image_queue_outgoing self.cancellation_event = cancellation_event self.capture_event = capture_event self.eye_id = eye_id - + # Cross algo state self.lkg_projected_sphere = None self.xc = None self.yc = None - + # Image state self.previous_image = None self.current_image = None @@ -134,14 +131,14 @@ class EyeProcessor: self.current_frame_number = None self.current_fps = None self.threshold_image = None - + # Calibration Values self.xoff = 1 self.yoff = 1 # Keep large in order to recenter correctly self.calibration_frame_counter = None self.eyeoffx = 1 - + self.xmax = -69420 self.xmin = 69420 self.ymax = -69420 @@ -150,41 +147,44 @@ class EyeProcessor: self.cccs = False self.ts = 10 self.previous_rotation = self.config.rotation_angle + self.calibration_frame_counter self.camera_model = None self.detector_3d = None - + self.camera_model = None self.detector_3d = None - + self.failed = 0 - + self.skip_blink_detect = False - - # blink + + #blink self.max_ints = [] self.max_int = 0 self.min_int = 4000000000000 - self.frames = 0 + self.frames = 0 self.blinkvalue = False self.prev_x = None self.prev_y = None + + try: min_cutoff = float(self.settings.gui_min_cutoff) # 0.0004 beta = float(self.settings.gui_speed_coefficient) # 0.9 except: - print("\033[93m[WARN] OneEuroFilter values must be a legal number.\033[0m") + print('\033[93m[WARN] OneEuroFilter values must be a legal number.\033[0m') min_cutoff = 0.0004 beta = 0.9 noisy_point = np.array([1, 1]) self.one_euro_filter = OneEuroFilter( - noisy_point, min_cutoff=min_cutoff, beta=beta + noisy_point, + min_cutoff=min_cutoff, + beta=beta ) - - def output_images_and_update( - self, threshold_image, output_information: EyeInformation - ): + + def output_images_and_update(self, threshold_image, output_information: EyeInformation): try: image_stack = np.concatenate( ( @@ -196,32 +196,29 @@ class EyeProcessor: self.image_queue_outgoing.put((image_stack, output_information)) self.previous_image = self.current_image self.previous_rotation = self.config.rotation_angle - except: # If this fails it likely means that the images are not the same size for some reason. - print( - "\033[91m[ERROR] Size of frames to display are of unequal sizes.\033[0m" - ) - + except: # If this fails it likely means that the images are not the same size for some reason. + print('\033[91m[ERROR] Size of frames to display are of unequal sizes.\033[0m') + pass - def capture_crop_rotate_image(self): # Get our current frame try: # Get frame from capture source, crop to ROI self.current_image = self.current_image[ - int(self.config.roi_window_y): int( - self.config.roi_window_y + self.config.roi_window_h - ), - int(self.config.roi_window_x): int( - self.config.roi_window_x + self.config.roi_window_w - ), - ] - + int(self.config.roi_window_y): int( + self.config.roi_window_y + self.config.roi_window_h + ), + int(self.config.roi_window_x): int( + self.config.roi_window_x + self.config.roi_window_w + ), + ] + except: # Failure to process frame, reuse previous frame. self.current_image = self.previous_image print("\033[91m[ERROR] Frame capture issue detected.\033[0m") - + try: # Apply rotation to cropped area. For any rotation area outside of the bounds of the image, # fill with white. @@ -243,119 +240,96 @@ class EyeProcessor: return True except: pass - + def BLINKM(self): self.blinkvalue = BLINK(self) - + + def HSRACM(self): - # temporary implementation - cx, cy, thresh, gray_frame, uncropframe = External_Run_HSRACS().run( - self.current_image_gray - ) + cx, cy, thresh, gray_frame, uncropframe = External_Run_HSRACS.HSRACS(self) self.current_image_gray = gray_frame - if self.prev_x is None: + if self.prev_x == None: self.prev_x = cx self.prev_y = cy - # print(self.prev_x, self.prev_y, cx, cy) + #print(self.prev_x, self.prev_y, cx, cy) # #filter values with too much movement - # if (cx - self.prev_x) <= 45 and (cy - self.prev_y) <= 45 : - # self.prev_x = cx - # self.prev_y = cy + # if (cx - self.prev_x) <= 45 and (cy - self.prev_y) <= 45 : + # self.prev_x = cx + # self.prev_y = cy eyeopen = intense(cx, cy, uncropframe) out_x, out_y = cal_osc(self, cx, cy) - + if cx == 0: - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen), - ) # update app + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen)) #update app else: - - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen), - ) - - # else: - # print("EYE MOVED TOO FAST") - # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, 0, 0, 0, False)) + + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen)) + # else: + # print("EYE MOVED TOO FAST") + # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, 0, 0, 0, False)) def HSFM(self): - # temporary implementation - cx, cy, frame = External_Run_HSF().run(self.current_image_gray) + cx, cy, frame = External_Run_HSF.HSFS(self) eyeopen = intense(cx, cy, self.current_image_gray) out_x, out_y = cal_osc(self, cx, cy) if cx == 0: - self.output_images_and_update( - frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, eyeopen) - ) # update app + self.output_images_and_update(frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, eyeopen)) #update app else: - self.output_images_and_update( - frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, eyeopen) - ) - + self.output_images_and_update(frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, eyeopen)) + def RANSAC3DM(self): cx, cy, thresh = RANSAC3D(self) eyeopen = intense(cx, cy, self.current_image_gray) out_x, out_y = cal_osc(self, cx, cy) if cx == 0: - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, eyeopen), - ) # update app + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, eyeopen)) #update app else: - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, eyeopen), - ) - + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, eyeopen)) + def BLOBM(self): cx, cy, thresh = BLOB(self) eyeopen = intense(cx, cy, self.current_image_gray) out_x, out_y = cal_osc(self, cx, cy) if cx == 0: - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen), - ) # update app + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen)) #update app else: - self.output_images_and_update( - thresh, - EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen), - ) - - def ALGOSELECT(self): + self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, eyeopen)) - if self.failed == 0 and self.firstalgo is not None: + + + def ALGOSELECT(self): + + if self.failed == 0 and self.firstalgo != None: self.firstalgo() else: self.failed = self.failed + 1 - - if ( - self.failed == 1 and self.secondalgo is not None - ): # send the tracking algos previous fail number, in algo if we pass set to 0, if fail, + 1 + + if self.failed == 1 and self.secondalgo != None: #send the tracking algos previous fail number, in algo if we pass set to 0, if fail, + 1 self.secondalgo() else: self.failed = self.failed + 1 - - if self.failed == 2 and self.thirdalgo is not None: + + if self.failed == 2 and self.thirdalgo != None: self.thirdalgo() else: self.failed = self.failed + 1 - - if self.failed == 3 and self.fourthalgo is not None: + + if self.failed == 3 and self.fourthalgo != None: self.fourthalgo() else: - self.failed = 0 # we have reached last possible algo and it is disabled, move to first algo - + self.failed = 0 # we have reached last possible algo and it is disabled, move to first algo + + + + def run(self): - + self.firstalgo = None self.secondalgo = None self.thirdalgo = None self.fourthalgo = None - # set algo priorities - - if (self.settings.gui_HSF and self.settings.gui_HSFP == 1): # I feel like this is super innefficient though it only runs at startup and no solution is coming to me atm + #set algo priorities + + if self.settings.gui_HSF and self.settings.gui_HSFP == 1: #I feel like this is super innefficient though it only runs at startup and no solution is coming to me atm self.firstalgo = self.HSFM elif self.settings.gui_HSF and self.settings.gui_HSFP == 2: self.secondalgo = self.HSFM @@ -363,7 +337,7 @@ class EyeProcessor: self.thirdalgo = self.HSFM elif self.settings.gui_HSF and self.settings.gui_HSFP == 4: self.fourthalgo = self.HSFM - + if self.settings.gui_RANSAC3D and self.settings.gui_RANSAC3DP == 1: self.firstalgo = self.RANSAC3DM elif self.settings.gui_RANSAC3D and self.settings.gui_RANSAC3DP == 2: @@ -372,8 +346,8 @@ class EyeProcessor: self.thirdalgo = self.RANSAC3DM elif self.settings.gui_RANSAC3D and self.settings.gui_RANSAC3DP == 4: self.fourthalgo = self.RANSAC3DM - - if self.settings.gui_HSRAC and self.settings.gui_HSRACP == 1: + + if self.settings.gui_HSRAC == True and self.settings.gui_HSRACP == 1: self.firstalgo = self.HSRACM elif self.settings.gui_HSRAC and self.settings.gui_HSRACP == 2: self.secondalgo = self.HSRACM @@ -381,7 +355,7 @@ class EyeProcessor: self.thirdalgo = self.HSRACM elif self.settings.gui_HSRAC and self.settings.gui_HSRACP == 4: self.fourthalgo = self.HSRACM - + if self.settings.gui_BLOB and self.settings.gui_BLOBP == 1: self.firstalgo = self.BLOBM elif self.settings.gui_BLOB and self.settings.gui_BLOBP == 2: @@ -390,31 +364,31 @@ class EyeProcessor: self.thirdalgo = self.BLOBM elif self.settings.gui_BLOB and self.settings.gui_BLOBP == 4: self.fourthalgo = self.BLOBM - + f = True while True: - # f = True - # Check to make sure we haven't been requested to close + # f = True + # Check to make sure we haven't been requested to close if self.cancellation_event.is_set(): print("\033[94m[INFO] Exiting Tracking thread\033[0m") return - + if self.config.roi_window_w <= 0 or self.config.roi_window_h <= 0: # At this point, we're waiting for the user to set up the ROI window in the GUI. # Sleep a bit while we wait. if self.cancellation_event.wait(0.1): return continue + + # If our ROI configuration has changed, reset our model and detector - if ( - self.camera_model is None - or self.detector_3d is None - or self.camera_model.resolution - != ( + if (self.camera_model is None + or self.detector_3d is None + or self.camera_model.resolution != ( self.config.roi_window_w, self.config.roi_window_h, - ) + ) ): self.camera_model = CameraModel( focal_length=self.config.focal_length, @@ -423,7 +397,7 @@ class EyeProcessor: self.detector_3d = Detector3D( camera=self.camera_model, long_term_mode=DetectorMode.blocking ) - + try: if self.capture_queue_incoming.empty(): self.capture_event.set() @@ -439,35 +413,41 @@ class EyeProcessor: if not self.capture_crop_rotate_image(): continue + self.current_image_gray = cv2.cvtColor( - self.current_image, cv2.COLOR_BGR2GRAY + self.current_image, cv2.COLOR_BGR2GRAY ) - self.current_image_gray_clean = ( - self.current_image_gray.copy() - ) # copy this frame to have a clean image for blink algo - # print(self.settings.gui_RANSAC3D) + self.current_image_gray_clean = self.current_image_gray.copy() #copy this frame to have a clean image for blink algo + # print(self.settings.gui_RANSAC3D) + + # BLINK(self) + + # cx, cy, thresh = HSRAC(self) + # out_x, out_y = cal_osc(self, cx, cy) + # if cx == 0: + # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, True)) #update app + # else: + # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, self.blinkvalue)) - # BLINK(self) + + # cx, cy, thresh = RANSAC3D(self) + # out_x, out_y = cal_osc(self, cx, cy) + # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, False)) #update app + + + # cx, cy, larger_threshold = BLOB(self) + # out_x, out_y = cal_osc(self, cx, cy) + # self.output_images_and_update(larger_threshold, EyeInformation(InformationOrigin.BLOB, out_x, out_y, 0, False)) #update app + + #center_x, center_y, frame = HSF(self) #run algo + #out_x, out_y = cal_osc(self, center_x, center_y) #filter and calibrate + #self.output_images_and_update(frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, False)) #update app - # cx, cy, thresh = HSRAC(self) - # out_x, out_y = cal_osc(self, cx, cy) - # if cx == 0: - # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, True)) #update app - # else: - # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, self.blinkvalue)) - - # cx, cy, thresh = RANSAC3D(self) - # out_x, out_y = cal_osc(self, cx, cy) - # self.output_images_and_update(thresh, EyeInformation(InformationOrigin.RANSAC, out_x, out_y, 0, False)) #update app - - # cx, cy, larger_threshold = BLOB(self) - # out_x, out_y = cal_osc(self, cx, cy) - # self.output_images_and_update(larger_threshold, EyeInformation(InformationOrigin.BLOB, out_x, out_y, 0, False)) #update app - - # center_x, center_y, frame = HSF(self) #run algo - # out_x, out_y = cal_osc(self, center_x, center_y) #filter and calibrate - # self.output_images_and_update(frame, EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, False)) #update app - - self.ALGOSELECT() # run our algos in priority order set in settings + self.ALGOSELECT() #run our algos in priority order set in settings self.BLINKM() + + + + + diff --git a/EyeTrackApp/haar_surround_feature.py b/EyeTrackApp/haar_surround_feature.py index e07496b..bbbe36b 100644 --- a/EyeTrackApp/haar_surround_feature.py +++ b/EyeTrackApp/haar_surround_feature.py @@ -7,8 +7,6 @@ from functools import lru_cache import cv2 import numpy as np -from EyeTrackApp.img_utils import safe_crop - # from line_profiler_pycharm import profile video_path = "ezgif.com-gif-maker.avi" @@ -29,6 +27,180 @@ blink_init_frames = 60 * 3 # 60fps*3sec,Number of blink statistical frames # step==(x,y) default_step = (5, 5) # bigger the steps,lower the processing time! ofc acc also takes an impact +""" +Attention. +If using cv2.filter2D in this code, be careful with the kernel +https://stackoverflow.com/questions/39457468/convolution-without-any-padding-opencv-python +""" + + +def TimeitWrapper(*args, **kwargs): + """ + This decorator @TimeitWrapper() prints the function name and execution time in seconds. + :param args: + :param kwargs: + :return: + """ + + def decorator(function): + @functools.wraps(function) + def wrapper(*args, **kwargs): + start = timeit.default_timer() + results = function(*args, **kwargs) + end = timeit.default_timer() + print('{} execution time: {:.10f} s'.format(function.__name__, end - start)) + return results + + return wrapper + + return decorator + + +class TimeitResult(object): + """ + from https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + + Object returned by the timeit magic with info about the run. + Contains the following attributes : + loops: (int) number of loops done per measurement + repeat: (int) number of times the measurement has been repeated + best: (float) best execution time / number + all_runs: (list of float) execution time of each run (in s) + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = best + self.worst = worst + self.all_runs = all_runs + self._precision = precision + self.timings = [dt / self.loops for dt in all_runs] + + @property + def average(self): + return math.fsum(self.timings) / len(self.timings) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.timings]) / len(self.timings)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean=format_time(self.average, self._precision), + std=format_time(self.stdev, self._precision), + best=format_time(self.best, self._precision), + worst=format_time(self.worst, self._precision), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +class FPSResult(object): + """ + base https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = 1 / best + self.worst = 1 / worst + self.all_runs = all_runs + self._precision = precision + self.fps = [1 / dt for dt in all_runs] + self.unit = "fps" + + @property + def average(self): + return math.fsum(self.fps) / len(self.fps) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.fps]) / len(self.fps)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean="%.*g%s" % (self._precision, self.average, self.unit), + std="%.*g%s" % (self._precision, self.stdev, self.unit), + best="%.*g%s" % (self._precision, self.best, self.unit), + worst="%.*g%s" % (self._precision, self.worst, self.unit), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +def format_time(timespan, precision=3): + """ + https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L1473 + Formats the timespan in a human readable form + """ + + if timespan >= 60.0: + # we have more than a minute, format that in a human readable form + # Idea from http://snipplr.com/view/5713/ + parts = [("d", 60 * 60 * 24), ("h", 60 * 60), ("min", 60), ("s", 1)] + time = [] + leftover = timespan + for suffix, length in parts: + value = int(leftover / length) + if value > 0: + leftover = leftover % length + time.append(u'%s%s' % (str(value), suffix)) + if leftover < 1: + break + return " ".join(time) + + # Unfortunately the unicode 'micro' symbol can cause problems in + # certain terminals. + # See bug: https://bugs.launchpad.net/ipython/+bug/348466 + # Try to prevent crashes by being more secure than it needs to + # E.g. eclipse is able to print a µ, but has no sys.stdout.encoding set. + units = [u"s", u"ms", u'us', "ns"] # the save value + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb5'.encode(sys.stdout.encoding) + units = [u"s", u"ms", u'\xb5s', "ns"] + except: + pass + scaling = [1, 1e3, 1e6, 1e9] + + if timespan > 0.0: + order = min(-int(math.floor(math.log10(timespan)) // 3), 3) + else: + order = 3 + return u"%.*g %s" % (precision, timespan * scaling[order], units[order]) + class CvParameters: # It may be a little slower because a dict named "self" is read for each function call. @@ -39,42 +211,43 @@ class CvParameters: # self.prev_step=step self._step = step self._hsf = HaarSurroundFeature(radius) - + def get_rpsh(self): return self._radius, self.pad, self._step, self._hsf # Essentially, the following would be preferable, but it would take twice as long to call. # return self.radius, self.pad, self.step, self.hsf - + @property def radius(self): return self._radius - + @radius.setter def radius(self, now_radius): # self.prev_radius=self._radius self._radius = now_radius self.pad = 2 * now_radius self.hsf = now_radius - + @property def step(self): return self._step - + @step.setter def step(self, now_step): # self.prev_step=self.step self._step = now_step - + @property def hsf(self): return self._hsf - + @hsf.setter def hsf(self, now_radius): self._hsf = HaarSurroundFeature(now_radius) class HaarSurroundFeature: + def __init__(self, r_inner, r_outer=None, val=None): if r_outer is None: r_outer = r_inner * 3 @@ -82,33 +255,30 @@ class HaarSurroundFeature: r_inner2 = r_inner * r_inner count_inner = r_inner2 count_outer = r_outer * r_outer - r_inner2 - + if val is None: val_inner = 1.0 / r_inner2 val_outer = -val_inner * count_inner / count_outer - + else: val_inner = val[0] val_outer = val[1] - + self.val_in = np.array(val_inner, dtype=np.float64) self.val_out = np.array(val_outer, dtype=np.float64) self.r_in = r_inner self.r_out = r_outer - + def get_kernel(self): # Defined here, but not yet used? # Create a kernel filled with the value of self.val_out - kernel = ( - np.ones(shape=(2 * self.r_out - 1, 2 * self.r_out - 1), dtype=np.float64) - * self.val_out - ) - + kernel = np.ones(shape=(2 * self.r_out - 1, 2 * self.r_out - 1), dtype=np.float64) * self.val_out + # Set the values of the inner area of the kernel using array slicing - start = self.r_out - self.r_in - end = self.r_out + self.r_in - 1 + start = (self.r_out - self.r_in) + end = (self.r_out + self.r_in - 1) kernel[start:end, start:end] = self.val_in - + return kernel @@ -132,10 +302,10 @@ def frameint_get_xy_step(imageshape, xysteps, pad, start_offset=None, end_offset row -= 1 col -= 1 x_step, y_step = xysteps - + # This is not beautiful. start_pad_x = start_pad_y = end_pad_x = end_pad_y = pad - + if start_offset is not None: start_pad_x += start_offset[0] start_pad_y += start_offset[1] @@ -144,9 +314,9 @@ def frameint_get_xy_step(imageshape, xysteps, pad, start_offset=None, end_offset end_pad_y += end_offset[1] y_np = np.arange(start_pad_y, row - end_pad_y, y_step) x_np = np.arange(start_pad_x, col - end_pad_x, x_step) - + xy_np = (x_np, y_np) - + return xy_np @@ -162,14 +332,8 @@ def get_hsf_empty_array(len_syx, frameint_x, frame_int_dtype, fcshape): p10 = np.empty(len_syx, dtype=frame_int_dtype) response_list = np.empty(len_syx, dtype=np.float64) frame_conv = np.zeros(shape=fcshape[0], dtype=np.uint8) - frame_conv_stride = frame_conv[:: fcshape[1], :: fcshape[2]] - return ( - (inner_sum, outer_sum), - p_temp, - (p00, p11, p01, p10), - response_list, - (frame_conv, frame_conv_stride), - ) + frame_conv_stride = frame_conv[::fcshape[1], ::fcshape[2]] + return (inner_sum, outer_sum), p_temp, (p00, p11, p01, p10), response_list, (frame_conv, frame_conv_stride) # @profile @@ -188,39 +352,30 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list): # padding2 = 2 * padding f_shape = row - 2 * padding, col - 2 * padding r_in = kernel.r_in - + len_sx, len_sy = len(xy_steps_list[0]), len(xy_steps_list[1]) - inout_sum, p_temp, p_list, response_list, frameconvlist = get_hsf_empty_array( - (len_sy, len_sx), col + 1, frame_int.dtype, (f_shape, y_step, x_step) - ) + inout_sum, p_temp, p_list, response_list, frameconvlist = get_hsf_empty_array((len_sy, len_sx), col + 1, + frame_int.dtype, (f_shape, y_step, x_step)) inner_sum, outer_sum = inout_sum p00, p11, p01, p10 = p_list frame_conv, frame_conv_stride = frameconvlist - + y_rin_m = xy_steps_list[1] - r_in x_rin_m = xy_steps_list[0] - r_in y_rin_p = xy_steps_list[1] + r_in x_rin_p = xy_steps_list[0] + r_in # xx==(y,x),m==MINUS,p==PLUS, ex: mm==(y-,x-) - inarr_mm = frame_int[ - y_rin_m[0] : y_rin_m[-1] + 1 : y_step, x_rin_m[0] : x_rin_m[-1] + 1 : x_step - ] - inarr_mp = frame_int[ - y_rin_m[0] : y_rin_m[-1] + 1 : y_step, x_rin_p[0] : x_rin_p[-1] + 1 : x_step - ] - inarr_pm = frame_int[ - y_rin_p[0] : y_rin_p[-1] + 1 : y_step, x_rin_m[0] : x_rin_m[-1] + 1 : x_step - ] - inarr_pp = frame_int[ - y_rin_p[0] : y_rin_p[-1] + 1 : y_step, x_rin_p[0] : x_rin_p[-1] + 1 : x_step - ] - + inarr_mm = frame_int[y_rin_m[0]:y_rin_m[-1] + 1:y_step, x_rin_m[0]:x_rin_m[-1] + 1:x_step] + inarr_mp = frame_int[y_rin_m[0]:y_rin_m[-1] + 1:y_step, x_rin_p[0]:x_rin_p[-1] + 1:x_step] + inarr_pm = frame_int[y_rin_p[0]:y_rin_p[-1] + 1:y_step, x_rin_m[0]:x_rin_m[-1] + 1:x_step] + inarr_pp = frame_int[y_rin_p[0]:y_rin_p[-1] + 1:y_step, x_rin_p[0]:x_rin_p[-1] + 1:x_step] + # == inarr_mm + inarr_pp - inarr_mp - inarr_pm inner_sum[:, :] = inarr_mm inner_sum += inarr_pp inner_sum -= inarr_mp inner_sum -= inarr_pm - + # Bottleneck here, I want to make it smarter. Someone do it. # (y,x) # p00=max(y_ro_m,0),max(x_ro_m,0) @@ -246,40 +401,37 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list): # p11=np.take(np.take(frame_int, y_ro_p, axis=0, mode="clip"), x_ro_p, axis=1, mode="clip") # p01=np.take(np.take(frame_int, y_ro_m, axis=0, mode="clip"), x_ro_p, axis=1, mode="clip") # p10=np.take(np.take(frame_int, y_ro_p, axis=0, mode="clip"), x_ro_m, axis=1, mode="clip") - + outer_sum[:, :] = p00 + p11 - p01 - p10 - inner_sum - + np.multiply(kernel.val_in, inner_sum, dtype=np.float64, out=response_list) response_list += kernel.val_out * outer_sum - + # min_response, max_val, min_loc, max_loc = cv2.minMaxLoc(response_list) min_response, _, min_loc, _ = cv2.minMaxLoc(response_list) - - center = ( - (xy_steps_list[0][min_loc[0]] - padding), - (xy_steps_list[1][min_loc[1]] - padding), - ) - + + center = ((xy_steps_list[0][min_loc[0]] - padding), (xy_steps_list[1][min_loc[1]] - padding)) + frame_conv_stride[:, :] = response_list # or # frame_conv_stride[:, :] = response_list.astype(np.uint8) - + return frame_conv, min_response, center -class AutoRadiusCalc(object): +class Auto_Radius_Calc(object): def __init__(self): self.response_list = [] self.radius_cand_list = [] self.adj_comp_flag = False - + self.radius_middle_index = None - + self.left_item = None self.right_item = None self.left_index = None self.right_index = None - + def get_radius(self): prev_res_len = len(self.response_list) # adjustment of radius @@ -299,35 +451,21 @@ class AutoRadiusCalc(object): else: self.left_item = self.response_list[0] self.right_item = self.response_list[2] - self.radius_cand_list = [ - i - for i in range( - self.left_item[0], - self.right_item[0] + auto_radius_step, - auto_radius_step, - ) - ] + self.radius_cand_list = [i for i in range(self.left_item[0], self.right_item[0] + auto_radius_step, auto_radius_step)] self.left_index = 0 self.right_index = len(self.radius_cand_list) - 1 self.radius_middle_index = (self.left_index + self.right_index) // 2 self.adj_comp_flag = False return self.radius_cand_list[self.radius_middle_index] else: - if ( - self.left_index <= self.right_index - and self.left_index != self.radius_middle_index - ): - if (self.left_item[1] + self.response_list[-1][1]) < ( - self.right_item[1] + self.response_list[-1][1] - ): + if self.left_index <= self.right_index and self.left_index != self.radius_middle_index: + if (self.left_item[1] + self.response_list[-1][1]) < (self.right_item[1] + self.response_list[-1][1]): self.right_item = self.response_list[-1] self.right_index = self.radius_middle_index - 1 self.radius_middle_index = (self.left_index + self.right_index) // 2 self.adj_comp_flag = False return self.radius_cand_list[self.radius_middle_index] - if (self.left_item[1] + self.response_list[-1][1]) > ( - self.right_item[1] + self.response_list[-1][1] - ): + if (self.left_item[1] + self.response_list[-1][1]) > (self.right_item[1] + self.response_list[-1][1]): self.left_item = self.response_list[-1] self.left_index = self.radius_middle_index + 1 self.radius_middle_index = (self.left_index + self.right_index) // 2 @@ -335,13 +473,13 @@ class AutoRadiusCalc(object): return self.radius_cand_list[self.radius_middle_index] self.adj_comp_flag = True return self.radius_cand_list[self.radius_middle_index] - + def get_radius_base(self): """ Use it when the new version doesn't work well. :return: """ - + prev_res_len = len(self.response_list) # adjustment of radius if prev_res_len == 1: @@ -361,21 +499,11 @@ class AutoRadiusCalc(object): self.adj_comp_flag = True return default_radius elif sort_res[0] == auto_radius_range[0]: - self.radius_cand_list = [ - i - for i in range( - auto_radius_range[0], default_radius, auto_radius_step - ) - ][1:] + self.radius_cand_list = [i for i in range(auto_radius_range[0], default_radius, auto_radius_step)][1:] self.adj_comp_flag = False return self.radius_cand_list.pop() else: - self.radius_cand_list = [ - i - for i in range( - default_radius, auto_radius_range[1], auto_radius_step - ) - ][1:] + self.radius_cand_list = [i for i in range(default_radius, auto_radius_range[1], auto_radius_step)][1:] self.adj_comp_flag = False return self.radius_cand_list.pop() else: @@ -388,19 +516,19 @@ class AutoRadiusCalc(object): else: self.adj_comp_flag = False return self.radius_cand_list.pop() - + def add_response(self, radius, response): self.response_list.append((radius, response)) return None -class BlinkDetector(object): +class Blink_Detector(object): def __init__(self): self.response_list = [] self.response_max = None self.enable_detect_flg = False self.quartile_1 = None - + def calc_thresh(self): # Calculate response_max by computing interquartile range, IQR # self.response_listo = np.array(self.response_listo) @@ -409,28 +537,28 @@ class BlinkDetector(object): # quartile_1, quartile_3 = np.percentile(self.response_listo, [25, 75]) # iqr = quartile_3 - quartile_1 # self.response_maxo = quartile_3 + (iqr * 1.5) - + # quartile_1, quartile_3 = np.percentile(self.response_list, [25, 75]) # or quartile_1, quartile_3 = np.percentile(np.array(self.response_list), [25, 75]) self.quartile_1 = quartile_1 iqr = quartile_3 - quartile_1 # response_min = quartile_1 - (iqr * 1.5) - + self.response_max = float(quartile_3 + (iqr * 1.5)) # or # self.response_max = quartile_3 + (iqr * 1.5) - + self.enable_detect_flg = True return None - + def detect(self, now_response): return now_response > self.response_max - + def add_response(self, response): self.response_list.append(response) return None - + def response_len(self): return len(self.response_list) @@ -441,7 +569,7 @@ class CenterCorrection(object): kernel_size = 7 # 3 or 5 or 7 self.hist_thr = float(4) # 4% self.center_q1_radius = 20 - + self.setup_comp = False self.quartile_1 = None self.radius = None @@ -449,14 +577,12 @@ class CenterCorrection(object): self.frame_mask = None self.frame_bin = None self.frame_final = None - self.morph_kernel = cv2.getStructuringElement( - cv2.MORPH_RECT, (kernel_size, kernel_size) - ) + self.morph_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_size, kernel_size)) self.morph_kernel2 = np.ones((3, 3)) self.hist_index = np.arange(256) self.hist = np.empty((256, 1)) self.hist_norm = np.empty((256, 1)) - + def init_array(self, gray_shape, quartile_1, radius): self.frame_shape = gray_shape self.frame_mask = np.empty(gray_shape, dtype=np.uint8) @@ -465,44 +591,34 @@ class CenterCorrection(object): self.quartile_1 = quartile_1 self.radius = radius self.setup_comp = True - + # def reset_array(self): # self.frame_mask.fill(0) - + def correction(self, gray_frame, orig_x, orig_y): center_x, center_y = orig_x, orig_y self.frame_mask.fill(0) - - # cv2.circle(self.frame_mask, center=(center_x, center_y), radius=int(self.radius * 2), color=255, thickness=-1) - + + # cv2.circle(self.frame_mask, center=(center_x, center_y), radius=int(self.radius * 2), color=255, thickness=-1) + # bottleneck cv2.calcHist([gray_frame], [0], None, [256], [0, 256], hist=self.hist) - + cv2.normalize(self.hist, self.hist_norm, alpha=100.0, norm_type=cv2.NORM_L1) hist_per = self.hist_norm.cumsum() hist_index_list = self.hist_index[hist_per >= self.hist_thr] - frame_thr = ( - hist_index_list[0] - if len(hist_index_list) - else np.percentile(cv2.bitwise_or(255 - self.frame_mask, gray_frame), 4) - ) - + frame_thr = hist_index_list[0] if len(hist_index_list) else np.percentile(cv2.bitwise_or(255 - self.frame_mask, gray_frame), 4) + # bottleneck - self.frame_bin = cv2.threshold(gray_frame, frame_thr, 1, cv2.THRESH_BINARY_INV)[ - 1 - ] + self.frame_bin = cv2.threshold(gray_frame, frame_thr, 1, cv2.THRESH_BINARY_INV)[1] cropped_x, cropped_y, cropped_w, cropped_h = cv2.boundingRect(self.frame_bin) - + self.frame_final = cv2.bitwise_and(self.frame_bin, self.frame_mask) - + # bottleneck - self.frame_final = cv2.morphologyEx( - self.frame_final, cv2.MORPH_CLOSE, self.morph_kernel - ) - self.frame_final = cv2.morphologyEx( - self.frame_final, cv2.MORPH_OPEN, self.morph_kernel - ) - + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_CLOSE, self.morph_kernel) + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_OPEN, self.morph_kernel) + if (cropped_h, cropped_w) == self.frame_shape: # Not detected. base_x, base_y = center_x, center_y @@ -511,54 +627,36 @@ class CenterCorrection(object): base_y = cropped_y + cropped_h // 2 if self.frame_final[base_y, base_x] != 1: if self.frame_final[center_y, center_x] != 1: - self.frame_final = cv2.morphologyEx( - self.frame_final, - cv2.MORPH_DILATE, - self.morph_kernel2, - iterations=3, - ) + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_DILATE, self.morph_kernel2, iterations=3) else: base_x, base_y = center_x, center_y - - contours, _ = cv2.findContours( - self.frame_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE - ) + + contours, _ = cv2.findContours(self.frame_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) contours_box = [cv2.boundingRect(cnt) for cnt in contours] contours_dist = np.array( - [ - abs(base_x - (cnt_x + cnt_w / 2)) + abs(base_y - (cnt_y + cnt_h / 2)) - for cnt_x, cnt_y, cnt_w, cnt_h in contours_box - ] - ) - + [abs(base_x - (cnt_x + cnt_w / 2)) + abs(base_y - (cnt_y + cnt_h / 2)) for cnt_x, cnt_y, cnt_w, cnt_h in contours_box]) + if len(contours_box): - cropped_x2, cropped_y2, cropped_w2, cropped_h2 = contours_box[ - contours_dist.argmin() - ] + cropped_x2, cropped_y2, cropped_w2, cropped_h2 = contours_box[contours_dist.argmin()] x = cropped_x2 + cropped_w2 // 2 y = cropped_y2 + cropped_h2 // 2 else: x = center_x y = center_y - + # if imshow_enable: # cv2.circle(frame, (orig_x, orig_y), 10, (255, 0, 0), -1) # cv2.circle(frame, (x, y), 7, (0, 0, 255), -1) - + # # out_x = center_x if abs(x - center_x) > radius else x # out_y = center_y if abs(y - center_y) > radius else y out_x, out_y = orig_x, orig_y - if ( - gray_frame[ - int(max(y - 5, 0)) : int(min(y + 5, self.frame_shape[0])), - int(max(x - 5, 0)) : int(min(x + 5, self.frame_shape[1])), - ].min() - < self.quartile_1 - ): + if gray_frame[int(max(y - 5, 0)):int(min(y + 5, self.frame_shape[0])), + int(max(x - 5, 0)):int(min(x + 5, self.frame_shape[1]))].min() < self.quartile_1: out_x = x out_y = y - + # if imshow_enable: # cv2.circle(frame, (out_x, out_y), 5, (0, 255, 0), -1) # @@ -567,36 +665,29 @@ class CenterCorrection(object): return out_x, out_y -# temporary name -class HSF_cls(object): +class HSRAC_cls(object): def __init__(self): # I'd like to take into account things like print, end_time - start_time processing time, etc., but it's too much trouble. - + # For measuring total processing time - + self.main_start_time = timeit.default_timer() - + self.rng = np.random.default_rng() self.cvparam = CvParameters(default_radius, default_step) - + self.cv_modeo = ["first_frame", "radius_adjust", "blink_adjust", "normal"] self.now_modeo = self.cv_modeo[0] - - self.auto_radius_calc = AutoRadiusCalc() - self.blink_detector = BlinkDetector() - self.center_q1 = BlinkDetector() + + self.auto_radius_calc = Auto_Radius_Calc() + self.blink_detector = Blink_Detector() + self.center_q1 = Blink_Detector() self.center_correct = CenterCorrection() - + self.cap = None - - self.timedict = { - "to_gray": [], - "int_img": [], - "conv_int": [], - "crop": [], - "total_cv": [], - } - + + self.timedict = {"to_gray": [], "int_img": [], "conv_int": [], "crop": [], "total_cv": []} + def open_video(self, video_path): # Temporary implementation to run cap = cv2.VideoCapture(video_path) @@ -604,7 +695,7 @@ class HSF_cls(object): raise IOError("Error opening video stream or file") self.cap = cap return True - + def read_frame(self): # Temporary implementation to run if not self.cap.isOpened(): @@ -615,53 +706,47 @@ class HSF_cls(object): self.current_image_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) return True return False - + def single_run(self): # Temporary implementation to run - + ## default_radius = 14 - + frame = self.current_image_gray if self.now_modeo == self.cv_modeo[1]: # adjustment of radius - + # debug print # if calc_print_enable: # temp_radius = self.auto_radius_calc.get_radius() # print('Now radius:', temp_radius) # self.cvparam.radius = temp_radius - + self.cvparam.radius = self.auto_radius_calc.get_radius() if self.auto_radius_calc.adj_comp_flag: - self.now_modeo = ( - self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3] - ) - + self.now_modeo = self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3] + radius, pad, step, hsf = self.cvparam.get_rpsh() - + # For measuring processing time of image processing cv_start_time = timeit.default_timer() - + gray_frame = frame self.timedict["to_gray"].append(timeit.default_timer() - cv_start_time) - + # Calculate the integral image of the frame int_start_time = timeit.default_timer() # BORDER_CONSTANT is faster than BORDER_REPLICATE There seems to be almost no negative impact when BORDER_CONSTANT is used. - frame_pad = cv2.copyMakeBorder( - gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT - ) + frame_pad = cv2.copyMakeBorder(gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT) frame_int = cv2.integral(frame_pad) self.timedict["int_img"].append(timeit.default_timer() - int_start_time) - + # Convolve the feature with the integral image conv_int_start_time = timeit.default_timer() - xy_step = frameint_get_xy_step( - frame_int.shape, step, pad, start_offset=None, end_offset=None - ) + xy_step = frameint_get_xy_step(frame_int.shape, step, pad, start_offset=None, end_offset=None) frame_conv, response, center_xy = conv_int(frame_int, hsf, step, pad, xy_step) self.timedict["conv_int"].append(timeit.default_timer() - conv_int_start_time) - + crop_start_time = timeit.default_timer() # Define the center point and radius center_x, center_y = center_xy @@ -669,10 +754,10 @@ class HSF_cls(object): lower_x = center_x - radius upper_y = center_y + radius lower_y = center_y - radius - + # Crop the image using the calculated bounds - cropped_image = safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y) - + cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] + if self.now_modeo == self.cv_modeo[0] or self.now_modeo == self.cv_modeo[1]: # If mode is first_frame or radius_adjust, record current radius and response self.auto_radius_calc.add_response(radius, response) @@ -680,19 +765,15 @@ class HSF_cls(object): # Statistics for blink detection if self.blink_detector.response_len() < blink_init_frames: self.blink_detector.add_response(cv2.mean(cropped_image)[0]) - + upper_x = center_x + self.center_correct.center_q1_radius lower_x = center_x - self.center_correct.center_q1_radius upper_y = center_y + self.center_correct.center_q1_radius lower_y = center_y - self.center_correct.center_q1_radius - self.center_q1.add_response( - cv2.mean(safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y))[ - 0 - ] - ) - + self.center_q1.add_response(cv2.mean(gray_frame[lower_y:upper_y, lower_x:upper_x])[0]) + else: - + self.blink_detector.calc_thresh() self.center_q1.calc_thresh() self.now_modeo = self.cv_modeo[3] @@ -709,15 +790,11 @@ class HSF_cls(object): # blink pass else: - # pass + # pass if not self.center_correct.setup_comp: - self.center_correct.init_array( - gray_frame.shape, self.center_q1.quartile_1, radius - ) - - center_x, center_y = self.center_correct.correction( - gray_frame, center_x, center_y - ) + self.center_correct.init_array(gray_frame.shape, self.center_q1.quartile_1, radius) + + center_x, center_y = self.center_correct.correction(gray_frame, center_x, center_y) # Define the center point and radius center_xy = (center_x, center_y) upper_x = center_x + radius @@ -725,29 +802,24 @@ class HSF_cls(object): upper_y = center_y + radius lower_y = center_y - radius # Crop the image using the calculated bounds - cropped_image = safe_crop( - gray_frame, lower_x, lower_y, upper_x, upper_y - ) - # if imshow_enable or save_video: - # cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1) - # cv2.circle(frame, (center_x, center_y), 3, (255, 0, 0), -1) + cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] + # if imshow_enable or save_video: + # cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1) + # cv2.circle(frame, (center_x, center_y), 3, (255, 0, 0), -1) # If you want to update response_max. it may be more cost-effective to rewrite response_list in the following way # https://stackoverflow.com/questions/42771110/fastest-way-to-left-cycle-a-numpy-array-like-pop-push-for-a-queue - + cv_end_time = timeit.default_timer() self.timedict["crop"].append(cv_end_time - crop_start_time) self.timedict["total_cv"].append(cv_end_time - cv_start_time) - - # if calc_print_enable: - # the lower the response the better the likelyhood of there being a pupil. you can adujst the radius and steps accordingly + + # if calc_print_enable: + # the lower the response the better the likelyhood of there being a pupil. you can adujst the radius and steps accordingly # print('Kernel response:', response) - # print('Pixel position:', center_xy) - + # print('Pixel position:', center_xy) + if imshow_enable: - if ( - self.now_modeo != self.cv_modeo[0] - and self.now_modeo != self.cv_modeo[1] - ): + if self.now_modeo != self.cv_modeo[0] and self.now_modeo != self.cv_modeo[1]: if 0 in cropped_image.shape: # If shape contains 0, it is not detected well. pass @@ -756,7 +828,7 @@ class HSF_cls(object): cv2.imshow("frame", frame) if cv2.waitKey(1) & 0xFF == ord("q"): pass - + if self.now_modeo == self.cv_modeo[0]: # Moving from first_frame to the next mode if skip_autoradius and skip_blink_detect: @@ -765,22 +837,20 @@ class HSF_cls(object): self.now_modeo = self.cv_modeo[2] else: self.now_modeo = self.cv_modeo[1] - + return center_x, center_y, frame +class External_Run_HSF: -class External_Run_HSF(object): - def __init__(self): - self.algo = HSF_cls() + hsrac = HSRAC_cls() - def run(self, current_image_gray): - self.algo.current_image_gray = current_image_gray - center_x, center_y, frame = self.algo.single_run() + def HSFS(self): + External_Run_HSF.hsrac.current_image_gray = self.current_image_gray + center_x, center_y, frame = External_Run_HSF.hsrac.single_run() return center_x, center_y, frame - -if __name__ == "__main__": - hsf = HSF_cls() - hsf.open_video(video_path) - while hsf.read_frame(): - _ = hsf.single_run() +if __name__ == '__main__': + hsrac = HSRAC_cls() + hsrac.open_video(video_path) + while hsrac.read_frame(): + _ = hsrac.single_run() \ No newline at end of file diff --git a/EyeTrackApp/hsrac.py b/EyeTrackApp/hsrac.py index 5bb344d..e5826f8 100644 --- a/EyeTrackApp/hsrac.py +++ b/EyeTrackApp/hsrac.py @@ -1,3 +1,4 @@ +import functools import math import sys import timeit @@ -6,23 +7,8 @@ from functools import lru_cache import cv2 import numpy as np -from EyeTrackApp.haar_surround_feature import ( - AutoRadiusCalc, - BlinkDetector, - CenterCorrection, - CvParameters, - conv_int, - frameint_get_xy_step, -) -from EyeTrackApp.img_utils import safe_crop -from EyeTrackApp.utils import clamp - # from line_profiler_pycharm import profile -# RANSAC - -thresh_add = 10 - video_path = "ezgif.com-gif-maker.avi" imshow_enable = True calc_print_enable = True @@ -41,6 +27,799 @@ blink_init_frames = 60 * 3 # 60fps*3sec,Number of blink statistical frames # step==(x,y) default_step = (5, 5) # bigger the steps,lower the processing time! ofc acc also takes an impact +""" +Attention. +If using cv2.filter2D in this code, be careful with the kernel +https://stackoverflow.com/questions/39457468/convolution-without-any-padding-opencv-python +""" + + +def TimeitWrapper(*args, **kwargs): + """ + This decorator @TimeitWrapper() prints the function name and execution time in seconds. + :param args: + :param kwargs: + :return: + """ + + def decorator(function): + @functools.wraps(function) + def wrapper(*args, **kwargs): + start = timeit.default_timer() + results = function(*args, **kwargs) + end = timeit.default_timer() + print('{} execution time: {:.10f} s'.format(function.__name__, end - start)) + return results + + return wrapper + + return decorator + + +class TimeitResult(object): + """ + from https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + + Object returned by the timeit magic with info about the run. + Contains the following attributes : + loops: (int) number of loops done per measurement + repeat: (int) number of times the measurement has been repeated + best: (float) best execution time / number + all_runs: (list of float) execution time of each run (in s) + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = best + self.worst = worst + self.all_runs = all_runs + self._precision = precision + self.timings = [dt / self.loops for dt in all_runs] + + @property + def average(self): + return math.fsum(self.timings) / len(self.timings) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.timings]) / len(self.timings)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean=format_time(self.average, self._precision), + std=format_time(self.stdev, self._precision), + best=format_time(self.best, self._precision), + worst=format_time(self.worst, self._precision), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +class FPSResult(object): + """ + base https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = 1 / best + self.worst = 1 / worst + self.all_runs = all_runs + self._precision = precision + self.fps = [1 / dt for dt in all_runs] + self.unit = "fps" + + @property + def average(self): + return math.fsum(self.fps) / len(self.fps) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.fps]) / len(self.fps)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean="%.*g%s" % (self._precision, self.average, self.unit), + std="%.*g%s" % (self._precision, self.stdev, self.unit), + best="%.*g%s" % (self._precision, self.best, self.unit), + worst="%.*g%s" % (self._precision, self.worst, self.unit), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +def format_time(timespan, precision=3): + """ + https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L1473 + Formats the timespan in a human readable form + """ + + if timespan >= 60.0: + # we have more than a minute, format that in a human readable form + # Idea from http://snipplr.com/view/5713/ + parts = [("d", 60 * 60 * 24), ("h", 60 * 60), ("min", 60), ("s", 1)] + time = [] + leftover = timespan + for suffix, length in parts: + value = int(leftover / length) + if value > 0: + leftover = leftover % length + time.append(u'%s%s' % (str(value), suffix)) + if leftover < 1: + break + return " ".join(time) + + # Unfortunately the unicode 'micro' symbol can cause problems in + # certain terminals. + # See bug: https://bugs.launchpad.net/ipython/+bug/348466 + # Try to prevent crashes by being more secure than it needs to + # E.g. eclipse is able to print a µ, but has no sys.stdout.encoding set. + units = [u"s", u"ms", u'us', "ns"] # the save value + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb5'.encode(sys.stdout.encoding) + units = [u"s", u"ms", u'\xb5s', "ns"] + except: + pass + scaling = [1, 1e3, 1e6, 1e9] + + if timespan > 0.0: + order = min(-int(math.floor(math.log10(timespan)) // 3), 3) + else: + order = 3 + return u"%.*g %s" % (precision, timespan * scaling[order], units[order]) + + +class CvParameters: + # It may be a little slower because a dict named "self" is read for each function call. + def __init__(self, radius, step): + # self.prev_radius=radius + self._radius = radius + self.pad = 2 * radius + # self.prev_step=step + self._step = step + self._hsf = HaarSurroundFeature(radius) + + def get_rpsh(self): + return self._radius, self.pad, self._step, self._hsf + # Essentially, the following would be preferable, but it would take twice as long to call. + # return self.radius, self.pad, self.step, self.hsf + + @property + def radius(self): + return self._radius + + @radius.setter + def radius(self, now_radius): + # self.prev_radius=self._radius + self._radius = now_radius + self.pad = 2 * now_radius + self.hsf = now_radius + + @property + def step(self): + return self._step + + @step.setter + def step(self, now_step): + # self.prev_step=self.step + self._step = now_step + + @property + def hsf(self): + return self._hsf + + @hsf.setter + def hsf(self, now_radius): + self._hsf = HaarSurroundFeature(now_radius) + + +class HaarSurroundFeature: + + def __init__(self, r_inner, r_outer=None, val=None): + if r_outer is None: + r_outer = r_inner * 3 + # print(r_outer) + r_inner2 = r_inner * r_inner + count_inner = r_inner2 + count_outer = r_outer * r_outer - r_inner2 + + if val is None: + val_inner = 1.0 / r_inner2 + val_outer = -val_inner * count_inner / count_outer + + else: + val_inner = val[0] + val_outer = val[1] + + self.val_in = np.array(val_inner, dtype=np.float64) + self.val_out = np.array(val_outer, dtype=np.float64) + self.r_in = r_inner + self.r_out = r_outer + + def get_kernel(self): + # Defined here, but not yet used? + # Create a kernel filled with the value of self.val_out + kernel = np.ones(shape=(2 * self.r_out - 1, 2 * self.r_out - 1), dtype=np.float64) * self.val_out + + # Set the values of the inner area of the kernel using array slicing + start = (self.r_out - self.r_in) + end = (self.r_out + self.r_in - 1) + kernel[start:end, start:end] = self.val_in + + return kernel + + +def to_gray(frame): + # Faster by quitting checking if the input image is already grayscale + # Perhaps it would be faster with less overhead to call cv2.cvtColor directly instead of using this function + return cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) + + +@lru_cache(maxsize=lru_maxsize_vs) +def frameint_get_xy_step(imageshape, xysteps, pad, start_offset=None, end_offset=None): + """ + :param imageshape: (height(row),width(col)). row==y,cal==x + :param xysteps: (x,y) + :param pad: int + :param start_offset: (x,y) or None + :param end_offset: (x,y) or None + :return: xy_np:tuple(x,y) + """ + row, col = imageshape + row -= 1 + col -= 1 + x_step, y_step = xysteps + + # This is not beautiful. + start_pad_x = start_pad_y = end_pad_x = end_pad_y = pad + + if start_offset is not None: + start_pad_x += start_offset[0] + start_pad_y += start_offset[1] + if end_offset is not None: + end_pad_x += end_offset[0] + end_pad_y += end_offset[1] + y_np = np.arange(start_pad_y, row - end_pad_y, y_step) + x_np = np.arange(start_pad_x, col - end_pad_x, x_step) + + xy_np = (x_np, y_np) + + return xy_np + + +@lru_cache(maxsize=lru_maxsize_vvs) +def get_hsf_empty_array(len_syx, frameint_x, frame_int_dtype, fcshape): + # Function to reduce array allocation by providing an empty array first and recycling it with lru + inner_sum = np.empty(len_syx, dtype=frame_int_dtype) + outer_sum = np.empty(len_syx, dtype=frame_int_dtype) + p_temp = np.empty((len_syx[0], frameint_x), dtype=frame_int_dtype) + p00 = np.empty(len_syx, dtype=frame_int_dtype) + p11 = np.empty(len_syx, dtype=frame_int_dtype) + p01 = np.empty(len_syx, dtype=frame_int_dtype) + p10 = np.empty(len_syx, dtype=frame_int_dtype) + response_list = np.empty(len_syx, dtype=np.float64) + frame_conv = np.zeros(shape=fcshape[0], dtype=np.uint8) + frame_conv_stride = frame_conv[::fcshape[1], ::fcshape[2]] + return (inner_sum, outer_sum), p_temp, (p00, p11, p01, p10), response_list, (frame_conv, frame_conv_stride) + + +# @profile +def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list): + """ + :param frame_int: + :param kernel: hsf + :param step: (x,y) + :param padding: int + :return: + """ + row, col = frame_int.shape + row -= 1 + col -= 1 + x_step, y_step = xy_step + # padding2 = 2 * padding + f_shape = row - 2 * padding, col - 2 * padding + r_in = kernel.r_in + + len_sx, len_sy = len(xy_steps_list[0]), len(xy_steps_list[1]) + inout_sum, p_temp, p_list, response_list, frameconvlist = get_hsf_empty_array((len_sy, len_sx), col + 1, + frame_int.dtype, (f_shape, y_step, x_step)) + inner_sum, outer_sum = inout_sum + p00, p11, p01, p10 = p_list + frame_conv, frame_conv_stride = frameconvlist + + y_rin_m = xy_steps_list[1] - r_in + x_rin_m = xy_steps_list[0] - r_in + y_rin_p = xy_steps_list[1] + r_in + x_rin_p = xy_steps_list[0] + r_in + # xx==(y,x),m==MINUS,p==PLUS, ex: mm==(y-,x-) + inarr_mm = frame_int[y_rin_m[0]:y_rin_m[-1] + 1:y_step, x_rin_m[0]:x_rin_m[-1] + 1:x_step] + inarr_mp = frame_int[y_rin_m[0]:y_rin_m[-1] + 1:y_step, x_rin_p[0]:x_rin_p[-1] + 1:x_step] + inarr_pm = frame_int[y_rin_p[0]:y_rin_p[-1] + 1:y_step, x_rin_m[0]:x_rin_m[-1] + 1:x_step] + inarr_pp = frame_int[y_rin_p[0]:y_rin_p[-1] + 1:y_step, x_rin_p[0]:x_rin_p[-1] + 1:x_step] + + # == inarr_mm + inarr_pp - inarr_mp - inarr_pm + inner_sum[:, :] = inarr_mm + inner_sum += inarr_pp + inner_sum -= inarr_mp + inner_sum -= inarr_pm + + # Bottleneck here, I want to make it smarter. Someone do it. + # (y,x) + # p00=max(y_ro_m,0),max(x_ro_m,0) + # p11=min(y_ro_p,ylim),min(x_ro_p,xlim) + # p01=max(y_ro_m,0),min(x_ro_p,xlim) + # p10=min(y_ro_p,ylim),max(x_ro_m,0) + y_ro_m = xy_steps_list[1] - kernel.r_out + x_ro_m = xy_steps_list[0] - kernel.r_out + y_ro_p = xy_steps_list[1] + kernel.r_out + x_ro_p = xy_steps_list[0] + kernel.r_out + # p00 calc + np.take(frame_int, y_ro_m, axis=0, mode="clip", out=p_temp) + np.take(p_temp, x_ro_m, axis=1, mode="clip", out=p00) + # p01 calc + np.take(p_temp, x_ro_p, axis=1, mode="clip", out=p01) + # p11 calc + np.take(frame_int, y_ro_p, axis=0, mode="clip", out=p_temp) + np.take(p_temp, x_ro_p, axis=1, mode="clip", out=p11) + # p10 calc + np.take(p_temp, x_ro_m, axis=1, mode="clip", out=p10) + # the point is this + # p00=np.take(np.take(frame_int, y_ro_m, axis=0, mode="clip"), x_ro_m, axis=1, mode="clip") + # p11=np.take(np.take(frame_int, y_ro_p, axis=0, mode="clip"), x_ro_p, axis=1, mode="clip") + # p01=np.take(np.take(frame_int, y_ro_m, axis=0, mode="clip"), x_ro_p, axis=1, mode="clip") + # p10=np.take(np.take(frame_int, y_ro_p, axis=0, mode="clip"), x_ro_m, axis=1, mode="clip") + + outer_sum[:, :] = p00 + p11 - p01 - p10 - inner_sum + + np.multiply(kernel.val_in, inner_sum, dtype=np.float64, out=response_list) + response_list += kernel.val_out * outer_sum + + # min_response, max_val, min_loc, max_loc = cv2.minMaxLoc(response_list) + min_response, _, min_loc, _ = cv2.minMaxLoc(response_list) + + center = ((xy_steps_list[0][min_loc[0]] - padding), (xy_steps_list[1][min_loc[1]] - padding)) + + frame_conv_stride[:, :] = response_list + # or + # frame_conv_stride[:, :] = response_list.astype(np.uint8) + + return frame_conv, min_response, center + + +class Auto_Radius_Calc(object): + def __init__(self): + self.response_list = [] + self.radius_cand_list = [] + self.adj_comp_flag = False + + self.radius_middle_index = None + + self.left_item = None + self.right_item = None + self.left_index = None + self.right_index = None + + def get_radius(self): + prev_res_len = len(self.response_list) + # adjustment of radius + if prev_res_len == 1: + # len==1==response_list==[default_radius] + self.adj_comp_flag = False + return auto_radius_range[0] + elif prev_res_len == 2: + # len==2==response_list==[default_radius, auto_radius_range[0]] + self.adj_comp_flag = False + return auto_radius_range[1] + elif prev_res_len == 3: + # len==3==response_list==[default_radius,auto_radius_range[0],auto_radius_range[1]] + if self.response_list[1][1] < self.response_list[2][1]: + self.left_item = self.response_list[1] + self.right_item = self.response_list[0] + else: + self.left_item = self.response_list[0] + self.right_item = self.response_list[2] + self.radius_cand_list = [i for i in range(self.left_item[0], self.right_item[0] + auto_radius_step, auto_radius_step)] + self.left_index = 0 + self.right_index = len(self.radius_cand_list) - 1 + self.radius_middle_index = (self.left_index + self.right_index) // 2 + self.adj_comp_flag = False + return self.radius_cand_list[self.radius_middle_index] + else: + if self.left_index <= self.right_index and self.left_index != self.radius_middle_index: + if (self.left_item[1] + self.response_list[-1][1]) < (self.right_item[1] + self.response_list[-1][1]): + self.right_item = self.response_list[-1] + self.right_index = self.radius_middle_index - 1 + self.radius_middle_index = (self.left_index + self.right_index) // 2 + self.adj_comp_flag = False + return self.radius_cand_list[self.radius_middle_index] + if (self.left_item[1] + self.response_list[-1][1]) > (self.right_item[1] + self.response_list[-1][1]): + self.left_item = self.response_list[-1] + self.left_index = self.radius_middle_index + 1 + self.radius_middle_index = (self.left_index + self.right_index) // 2 + self.adj_comp_flag = False + return self.radius_cand_list[self.radius_middle_index] + self.adj_comp_flag = True + return self.radius_cand_list[self.radius_middle_index] + + def get_radius_base(self): + """ + Use it when the new version doesn't work well. + :return: + """ + + prev_res_len = len(self.response_list) + # adjustment of radius + if prev_res_len == 1: + # len==1==response_list==[default_radius] + self.adj_comp_flag = False + return auto_radius_range[0] + elif prev_res_len == 2: + # len==2==response_list==[default_radius, auto_radius_range[0]] + self.adj_comp_flag = False + return auto_radius_range[1] + elif prev_res_len == 3: + # len==3==response_list==[default_radius,auto_radius_range[0],auto_radius_range[1]] + sort_res = sorted(self.response_list, key=lambda x: x[1])[0] + # Extract the radius with the lowest response value + if sort_res[0] == default_radius: + # If the default value is best, change now_mode to init after setting radius to the default value. + self.adj_comp_flag = True + return default_radius + elif sort_res[0] == auto_radius_range[0]: + self.radius_cand_list = [i for i in range(auto_radius_range[0], default_radius, auto_radius_step)][1:] + self.adj_comp_flag = False + return self.radius_cand_list.pop() + else: + self.radius_cand_list = [i for i in range(default_radius, auto_radius_range[1], auto_radius_step)][1:] + self.adj_comp_flag = False + return self.radius_cand_list.pop() + else: + # Try the contents of the radius_cand_list in order until the radius_cand_list runs out + # Better make it a binary search. + if len(self.radius_cand_list) == 0: + sort_res = sorted(self.response_list, key=lambda x: x[1])[0] + self.adj_comp_flag = True + return sort_res[0] + else: + self.adj_comp_flag = False + return self.radius_cand_list.pop() + + def add_response(self, radius, response): + self.response_list.append((radius, response)) + return None + + +class Blink_Detector(object): + def __init__(self): + self.response_list = [] + self.response_max = None + self.enable_detect_flg = False + self.quartile_1 = None + + def calc_thresh(self): + # Calculate response_max by computing interquartile range, IQR + # self.response_listo = np.array(self.response_listo) + # 25%,75% + # This value may need to be adjusted depending on the environment. + # quartile_1, quartile_3 = np.percentile(self.response_listo, [25, 75]) + # iqr = quartile_3 - quartile_1 + # self.response_maxo = quartile_3 + (iqr * 1.5) + + # quartile_1, quartile_3 = np.percentile(self.response_list, [25, 75]) + # or + quartile_1, quartile_3 = np.percentile(np.array(self.response_list), [25, 75]) + self.quartile_1 = quartile_1 + iqr = quartile_3 - quartile_1 + # response_min = quartile_1 - (iqr * 1.5) + + self.response_max = float(quartile_3 + (iqr * 1.5)) + # or + # self.response_max = quartile_3 + (iqr * 1.5) + + self.enable_detect_flg = True + return None + + def detect(self, now_response): + return now_response > self.response_max + + def add_response(self, response): + self.response_list.append(response) + return None + + def response_len(self): + return len(self.response_list) + + +class CenterCorrection(object): + def __init__(self): + # Tunable parameters + kernel_size = 7 # 3 or 5 or 7 + self.hist_thr = float(4) # 4% + self.center_q1_radius = 20 + + self.setup_comp = False + self.quartile_1 = None + self.radius = None + self.frame_shape = None + self.frame_mask = None + self.frame_bin = None + self.frame_final = None + self.morph_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_size, kernel_size)) + self.morph_kernel2 = np.ones((3, 3)) + self.hist_index = np.arange(256) + self.hist = np.empty((256, 1)) + self.hist_norm = np.empty((256, 1)) + + def init_array(self, gray_shape, quartile_1, radius): + self.frame_shape = gray_shape + self.frame_mask = np.empty(gray_shape, dtype=np.uint8) + self.frame_bin = np.empty(gray_shape, dtype=np.uint8) + self.frame_final = np.empty(gray_shape, dtype=np.uint8) + self.quartile_1 = quartile_1 + self.radius = radius + self.setup_comp = True + + # def reset_array(self): + # self.frame_mask.fill(0) + + def correction(self, gray_frame, orig_x, orig_y): + center_x, center_y = orig_x, orig_y + self.frame_mask.fill(0) + + # cv2.circle(self.frame_mask, center=(center_x, center_y), radius=int(self.radius * 2), color=255, thickness=-1) + + # bottleneck + cv2.calcHist([gray_frame], [0], None, [256], [0, 256], hist=self.hist) + + cv2.normalize(self.hist, self.hist_norm, alpha=100.0, norm_type=cv2.NORM_L1) + hist_per = self.hist_norm.cumsum() + hist_index_list = self.hist_index[hist_per >= self.hist_thr] + frame_thr = hist_index_list[0] if len(hist_index_list) else np.percentile(cv2.bitwise_or(255 - self.frame_mask, gray_frame), 4) + + # bottleneck + self.frame_bin = cv2.threshold(gray_frame, frame_thr, 1, cv2.THRESH_BINARY_INV)[1] + cropped_x, cropped_y, cropped_w, cropped_h = cv2.boundingRect(self.frame_bin) + + self.frame_final = cv2.bitwise_and(self.frame_bin, self.frame_mask) + + # bottleneck + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_CLOSE, self.morph_kernel) + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_OPEN, self.morph_kernel) + + if (cropped_h, cropped_w) == self.frame_shape: + # Not detected. + base_x, base_y = center_x, center_y + else: + base_x = cropped_x + cropped_w // 2 + base_y = cropped_y + cropped_h // 2 + if self.frame_final[base_y, base_x] != 1: + if self.frame_final[center_y, center_x] != 1: + self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_DILATE, self.morph_kernel2, iterations=3) + else: + base_x, base_y = center_x, center_y + + contours, _ = cv2.findContours(self.frame_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) + contours_box = [cv2.boundingRect(cnt) for cnt in contours] + contours_dist = np.array( + [abs(base_x - (cnt_x + cnt_w / 2)) + abs(base_y - (cnt_y + cnt_h / 2)) for cnt_x, cnt_y, cnt_w, cnt_h in contours_box]) + + if len(contours_box): + cropped_x2, cropped_y2, cropped_w2, cropped_h2 = contours_box[contours_dist.argmin()] + x = cropped_x2 + cropped_w2 // 2 + y = cropped_y2 + cropped_h2 // 2 + else: + x = center_x + y = center_y + + # if imshow_enable: + # cv2.circle(frame, (orig_x, orig_y), 10, (255, 0, 0), -1) + # cv2.circle(frame, (x, y), 7, (0, 0, 255), -1) + + # + # out_x = center_x if abs(x - center_x) > radius else x + # out_y = center_y if abs(y - center_y) > radius else y + out_x, out_y = orig_x, orig_y + if gray_frame[int(max(y - 5, 0)):int(min(y + 5, self.frame_shape[0])), + int(max(x - 5, 0)):int(min(x + 5, self.frame_shape[1]))].min() < self.quartile_1: + out_x = x + out_y = y + + # if imshow_enable: + # cv2.circle(frame, (out_x, out_y), 5, (0, 255, 0), -1) + # + # cv2.imshow("frame_bin", self.frame_bin * 255) + # cv2.imshow("frame_final", self.frame_final * 255) + return out_x, out_y + + +#RANSAC + + +video_path = "demo2.mp4" +imshow_enable = True +save_video = False + +thresh_add = 10 + + +class TimeitResult(object): + """ + from https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + + Object returned by the timeit magic with info about the run. + Contains the following attributes : + loops: (int) number of loops done per measurement + repeat: (int) number of times the measurement has been repeated + best: (float) best execution time / number + all_runs: (list of float) execution time of each run (in s) + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = best + self.worst = worst + self.all_runs = all_runs + self._precision = precision + self.timings = [dt / self.loops for dt in all_runs] + + @property + def average(self): + return math.fsum(self.timings) / len(self.timings) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.timings]) / len(self.timings)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean=format_time(self.average, self._precision), + std=format_time(self.stdev, self._precision), + best=format_time(self.best, self._precision), + worst=format_time(self.worst, self._precision), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +class FPSResult(object): + """ + base https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 + """ + + def __init__(self, loops, repeat, best, worst, all_runs, precision): + self.loops = loops + self.repeat = repeat + self.best = 1 / best + self.worst = 1 / worst + self.all_runs = all_runs + self._precision = precision + self.fps = [1 / dt for dt in all_runs] + self.unit = "fps" + + @property + def average(self): + return math.fsum(self.fps) / len(self.fps) + + @property + def stdev(self): + mean = self.average + return (math.fsum([(x - mean) ** 2 for x in self.fps]) / len(self.fps)) ** 0.5 + + def __str__(self): + pm = '+-' + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb1'.encode(sys.stdout.encoding) + pm = u'\xb1' + except: + pass + return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( + pm=pm, + runs=self.repeat, + loops=self.loops, + loop_plural="" if self.loops == 1 else "s", + run_plural="" if self.repeat == 1 else "s", + mean="%.*g%s" % (self._precision, self.average, self.unit), + std="%.*g%s" % (self._precision, self.stdev, self.unit), + best="%.*g%s" % (self._precision, self.best, self.unit), + worst="%.*g%s" % (self._precision, self.worst, self.unit), + ) + + def _repr_pretty_(self, p, cycle): + unic = self.__str__() + p.text(u'') + + +def format_time(timespan, precision=3): + """ + https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L1473 + Formats the timespan in a human readable form + """ + + if timespan >= 60.0: + # we have more than a minute, format that in a human readable form + # Idea from http://snipplr.com/view/5713/ + parts = [("d", 60 * 60 * 24), ("h", 60 * 60), ("min", 60), ("s", 1)] + time = [] + leftover = timespan + for suffix, length in parts: + value = int(leftover / length) + if value > 0: + leftover = leftover % length + time.append(u'%s%s' % (str(value), suffix)) + if leftover < 1: + break + return " ".join(time) + + # Unfortunately the unicode 'micro' symbol can cause problems in + # certain terminals. + # See bug: https://bugs.launchpad.net/ipython/+bug/348466 + # Try to prevent crashes by being more secure than it needs to + # E.g. eclipse is able to print a µ, but has no sys.stdout.encoding set. + units = [u"s", u"ms", u'us', "ns"] # the save value + if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: + try: + u'\xb5'.encode(sys.stdout.encoding) + units = [u"s", u"ms", u'\xb5s', "ns"] + except: + pass + scaling = [1, 1e3, 1e6, 1e9] + + if timespan > 0.0: + order = min(-int(math.floor(math.log10(timespan)) // 3), 3) + else: + order = 3 + return u"%.*g %s" % (precision, timespan * scaling[order], units[order]) + def ellipse_model(data, y, f): """ @@ -56,85 +835,59 @@ def ellipse_model(data, y, f): # @profile -def fit_rotated_ellipse_ransac( - data: np.ndarray, - rng: np.random.Generator, - iter=100, - sample_num=10, - offset=80, # 80.0, 10, 80 -): # before changing these values, please read up on the ransac algorithm +def fit_rotated_ellipse_ransac(data: np.ndarray, rng: np.random.Generator, iter=100, sample_num=10, offset=80 # 80.0, 10, 80 + ): # before changing these values, please read up on the ransac algorithm # However if you want to change any value just know that higher iterations will make processing frames slower effective_sample = None - + # The array contents do not change during the loop, so only one call is needed. # They say len is faster than shape. # Reference url: https://stackoverflow.com/questions/35547853/what-is-faster-python3s-len-or-numpys-shape len_data = len(data) - + if len_data < sample_num: return None - + # Type of calculation result ret_dtype = np.float64 - + # Sorts a random number array of size (iter,len_data). After sorting, returns the index of sample_num random numbers before sorting. # If the array size is less than about 100, this is faster than rng.choice. rng_sample = rng.random((iter, len_data)).argsort()[:, :sample_num] # or # I don't see any advantage to doing this. # rng_sample = np.asarray(rng.random((iter, len_data)).argsort()[:, :sample_num], dtype=np.int32) - + # I don't think it looks beautiful. # x,y,x**2,y**2,x*y,1,-1*x**2 datamod = np.concatenate( - [ - data, - data**2, - (data[:, 0] * data[:, 1])[:, np.newaxis], - np.ones((len_data, 1), dtype=ret_dtype), - (-1 * data[:, 0] ** 2)[:, np.newaxis], - ], - axis=1, - dtype=ret_dtype, - ) - + [data, data ** 2, (data[:, 0] * data[:, 1])[:, np.newaxis], np.ones((len_data, 1), dtype=ret_dtype), + (-1 * data[:, 0] ** 2)[:, np.newaxis]], axis=1, + dtype=ret_dtype) + datamod_slim = np.array(datamod[:, :5], dtype=ret_dtype) - + datamod_rng = datamod[rng_sample] datamod_rng6 = datamod_rng[:, :, 6] datamod_rng_swap = datamod_rng[:, :, [4, 3, 0, 1, 5]] datamod_rng_swap_trans = datamod_rng_swap.transpose((0, 2, 1)) - + # These two lines are one of the bottlenecks datamod_rng_5x5 = np.matmul(datamod_rng_swap_trans, datamod_rng_swap) - datamod_rng_p5smp = np.matmul( - np.linalg.inv(datamod_rng_5x5), datamod_rng_swap_trans - ) - - datamod_rng_p = np.matmul( - datamod_rng_p5smp, datamod_rng6[:, :, np.newaxis] - ).reshape((-1, 5)) - + datamod_rng_p5smp = np.matmul(np.linalg.inv(datamod_rng_5x5), datamod_rng_swap_trans) + + datamod_rng_p = np.matmul(datamod_rng_p5smp, datamod_rng6[:, :, np.newaxis]).reshape((-1, 5)) + # I don't think it looks beautiful. ellipse_y_arr = np.asarray( - [ - datamod_rng_p[:, 2], - datamod_rng_p[:, 3], - np.ones(len(datamod_rng_p)), - datamod_rng_p[:, 1], - datamod_rng_p[:, 0], - ], - dtype=ret_dtype, - ) - - ellipse_data_arr = ellipse_model( - datamod_slim, ellipse_y_arr, np.asarray(datamod_rng_p[:, 4]) - ).transpose((1, 0)) + [datamod_rng_p[:, 2], datamod_rng_p[:, 3], np.ones(len(datamod_rng_p)), datamod_rng_p[:, 1], datamod_rng_p[:, 0]], dtype=ret_dtype) + + ellipse_data_arr = ellipse_model(datamod_slim, ellipse_y_arr, np.asarray(datamod_rng_p[:, 4])).transpose((1, 0)) ellipse_data_abs = np.abs(ellipse_data_arr) ellipse_data_index = np.argmax(np.sum(ellipse_data_abs < offset, axis=1), axis=0) effective_data_arr = ellipse_data_arr[ellipse_data_index] effective_sample_p_arr = datamod_rng_p[ellipse_data_index] - + return fit_rotated_ellipse(effective_data_arr, effective_sample_p_arr) @@ -150,62 +903,60 @@ def fit_rotated_ellipse(data, P): theta = 0.5 * np.arctan(b / (a - c), dtype=np.float64) theta_sin = np.sin(theta, dtype=np.float64) theta_cos = np.cos(theta, dtype=np.float64) - tc2 = theta_cos**2 - ts2 = theta_sin**2 + tc2 = theta_cos ** 2 + ts2 = theta_sin ** 2 b_tcs = b * theta_cos * theta_sin - + # Do the calculation only once - cxy = b**2 - 4 * a * c + cxy = b ** 2 - 4 * a * c cx = (2 * c * d - b * e) / cxy cy = (2 * a * e - b * d) / cxy - + # I just want to clear things up around here. - cu = a * cx**2 + b * cx * cy + c * cy**2 - f + cu = a * cx ** 2 + b * cx * cy + c * cy ** 2 - f cu_r = np.array([(a * tc2 + b_tcs + c * ts2), (a * ts2 - b_tcs + c * tc2)]) wh = np.sqrt(cu / cu_r) - + w, h = wh[0], wh[1] - + error_sum = np.sum(data) # print("fitting error = %.3f" % (error_sum)) - + return (cx, cy, w, h, theta) -# temporary name + + + + + class HSRAC_cls(object): def __init__(self): # I'd like to take into account things like print, end_time - start_time processing time, etc., but it's too much trouble. - + # For measuring total processing time - + self.main_start_time = timeit.default_timer() - + self.rng = np.random.default_rng() self.cvparam = CvParameters(default_radius, default_step) - + self.cv_modeo = ["first_frame", "radius_adjust", "blink_adjust", "normal"] self.now_modeo = self.cv_modeo[0] - - self.auto_radius_calc = AutoRadiusCalc() - self.blink_detector = BlinkDetector() - self.center_q1 = BlinkDetector() + + self.auto_radius_calc = Auto_Radius_Calc() + self.blink_detector = Blink_Detector() + self.center_q1 = Blink_Detector() self.center_correct = CenterCorrection() - + self.cap = None - - self.timedict = { - "to_gray": [], - "int_img": [], - "conv_int": [], - "crop": [], - "total_cv": [], - } + + self.timedict = {"to_gray": [], "int_img": [], "conv_int": [], "crop": [], "total_cv": []} # ransac self.rng = np.random.default_rng() self.kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3)) - + def open_video(self, video_path): # Temporary implementation to run cap = cv2.VideoCapture(video_path) @@ -213,7 +964,7 @@ class HSRAC_cls(object): raise IOError("Error opening video stream or file") self.cap = cap return True - + def read_frame(self): # Temporary implementation to run if not self.cap.isOpened(): @@ -224,54 +975,49 @@ class HSRAC_cls(object): self.current_image_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) return True return False - + def single_run(self): # Temporary implementation to run - + ## default_radius = 14 - + frame = self.current_image_gray - + frame = cv2.copyMakeBorder(frame, 21, 21, 21, 21, cv2.BORDER_CONSTANT, value=[255, 255, 255]) # add a border to prevent overcropping the image. + if self.now_modeo == self.cv_modeo[1]: # adjustment of radius - + # debug print # if calc_print_enable: # temp_radius = self.auto_radius_calc.get_radius() # print('Now radius:', temp_radius) # self.cvparam.radius = temp_radius - + self.cvparam.radius = self.auto_radius_calc.get_radius() if self.auto_radius_calc.adj_comp_flag: - self.now_modeo = ( - self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3] - ) - + self.now_modeo = self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3] + radius, pad, step, hsf = self.cvparam.get_rpsh() - + # For measuring processing time of image processing cv_start_time = timeit.default_timer() - + gray_frame = frame self.timedict["to_gray"].append(timeit.default_timer() - cv_start_time) - + # Calculate the integral image of the frame int_start_time = timeit.default_timer() # BORDER_CONSTANT is faster than BORDER_REPLICATE There seems to be almost no negative impact when BORDER_CONSTANT is used. - frame_pad = cv2.copyMakeBorder( - gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT - ) + frame_pad = cv2.copyMakeBorder(gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT) frame_int = cv2.integral(frame_pad) self.timedict["int_img"].append(timeit.default_timer() - int_start_time) - + # Convolve the feature with the integral image conv_int_start_time = timeit.default_timer() - xy_step = frameint_get_xy_step( - frame_int.shape, step, pad, start_offset=None, end_offset=None - ) + xy_step = frameint_get_xy_step(frame_int.shape, step, pad, start_offset=None, end_offset=None) frame_conv, response, center_xy = conv_int(frame_int, hsf, step, pad, xy_step) self.timedict["conv_int"].append(timeit.default_timer() - conv_int_start_time) - + crop_start_time = timeit.default_timer() # Define the center point and radius center_x, center_y = center_xy @@ -279,10 +1025,10 @@ class HSRAC_cls(object): lower_x = center_x - radius upper_y = center_y + radius lower_y = center_y - radius - + # Crop the image using the calculated bounds - cropped_image = safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y) - + cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] + if self.now_modeo == self.cv_modeo[0] or self.now_modeo == self.cv_modeo[1]: # If mode is first_frame or radius_adjust, record current radius and response self.auto_radius_calc.add_response(radius, response) @@ -290,19 +1036,15 @@ class HSRAC_cls(object): # Statistics for blink detection if self.blink_detector.response_len() < blink_init_frames: self.blink_detector.add_response(cv2.mean(cropped_image)[0]) - + upper_x = center_x + self.center_correct.center_q1_radius lower_x = center_x - self.center_correct.center_q1_radius upper_y = center_y + self.center_correct.center_q1_radius lower_y = center_y - self.center_correct.center_q1_radius - self.center_q1.add_response( - cv2.mean(safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y))[ - 0 - ] - ) - + self.center_q1.add_response(cv2.mean(gray_frame[lower_y:upper_y, lower_x:upper_x])[0]) + else: - + self.blink_detector.calc_thresh() self.center_q1.calc_thresh() self.now_modeo = self.cv_modeo[3] @@ -319,15 +1061,11 @@ class HSRAC_cls(object): # blink pass else: - # pass + # pass if not self.center_correct.setup_comp: - self.center_correct.init_array( - gray_frame.shape, self.center_q1.quartile_1, radius - ) - - center_x, center_y = self.center_correct.correction( - gray_frame, center_x, center_y - ) + self.center_correct.init_array(gray_frame.shape, self.center_q1.quartile_1, radius) + + center_x, center_y = self.center_correct.correction(gray_frame, center_x, center_y) # Define the center point and radius center_xy = (center_x, center_y) upper_x = center_x + radius @@ -335,39 +1073,35 @@ class HSRAC_cls(object): upper_y = center_y + radius lower_y = center_y - radius # Crop the image using the calculated bounds - cropped_image = safe_crop( - gray_frame, lower_x, lower_y, upper_x, upper_y - ) - # if imshow_enable or save_video: - # cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1) - # cv2.circle(frame, (center_x, center_y), 3, (255, 0, 0), -1) + cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] + # if imshow_enable or save_video: + # cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1) + # cv2.circle(frame, (center_x, center_y), 3, (255, 0, 0), -1) # If you want to update response_max. it may be more cost-effective to rewrite response_list in the following way # https://stackoverflow.com/questions/42771110/fastest-way-to-left-cycle-a-numpy-array-like-pop-push-for-a-queue - + cv_end_time = timeit.default_timer() self.timedict["crop"].append(cv_end_time - crop_start_time) self.timedict["total_cv"].append(cv_end_time - cv_start_time) - - # if calc_print_enable: - # the lower the response the better the likelyhood of there being a pupil. you can adujst the radius and steps accordingly + + # if calc_print_enable: + # the lower the response the better the likelyhood of there being a pupil. you can adujst the radius and steps accordingly # print('Kernel response:', response) - # print('Pixel position:', center_xy) - + # print('Pixel position:', center_xy) + + if imshow_enable: - if ( - self.now_modeo != self.cv_modeo[0] - and self.now_modeo != self.cv_modeo[1] - ): + if self.now_modeo != self.cv_modeo[0] and self.now_modeo != self.cv_modeo[1]: if 0 in cropped_image.shape: # If shape contains 0, it is not detected well. pass else: - + cv2.imshow("crop", cropped_image) cv2.imshow("frame", frame) if cv2.waitKey(1) & 0xFF == ord("q"): pass - + if self.now_modeo == self.cv_modeo[0]: # Moving from first_frame to the next mode if skip_autoradius and skip_blink_detect: @@ -376,13 +1110,14 @@ class HSRAC_cls(object): self.now_modeo = self.cv_modeo[2] else: self.now_modeo = self.cv_modeo[1] + newFrame2 = frame.copy() - # frame = cropped_image + #frame = cropped_image # For measuring processing time of image processing cv_start_time = timeit.default_timer() # Crop first to reduce the amount of data to process. - # frame = cropped_image[0:len(cropped_image) - 10, :] + # frame = cropped_image[0:len(cropped_image) - 10, :] # To reduce the processing data, first convert to 1-channel and then blur. # The processing results were the same when I swapped the order of blurring and 1-channelization. frame_gray = cv2.GaussianBlur(frame, (5, 5), 0) @@ -393,21 +1128,21 @@ class HSRAC_cls(object): lower_y = center_y - 20 # Crop the image using the calculated bounds - - frame_gray = safe_crop(frame_gray, lower_x, lower_y, upper_x, upper_y) + + frame_gray = frame_gray[lower_y:upper_y, lower_x:upper_x] frame = frame_gray # this will need to be adjusted everytime hardware is changed (brightness of IR, Camera postion, etc)m min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(frame_gray) - + maxloc0_hf, maxloc1_hf = int(0.5 * max_loc[0]), int(0.5 * max_loc[1]) - + # crop 15% sqare around min_loc - # frame_gray = frame_gray[max_loc[1] - maxloc1_hf:max_loc[1] + maxloc1_hf, + # frame_gray = frame_gray[max_loc[1] - maxloc1_hf:max_loc[1] + maxloc1_hf, # max_loc[0] - maxloc0_hf:max_loc[0] + maxloc0_hf] - + threshold_value = min_val + thresh_add _, thresh = cv2.threshold(frame_gray, threshold_value, 255, cv2.THRESH_BINARY) - # print(thresh.shape, frame_gray.shape) + # print(thresh.shape, frame_gray.shape) try: opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, self.kernel) closing = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, self.kernel) @@ -426,10 +1161,10 @@ class HSRAC_cls(object): # If empty, go to next loop pass try: - + cnt = sorted(hull, key=cv2.contourArea) maxcnt = cnt[-1] - + # ellipse = cv2.fitEllipse(maxcnt) ransac_data = fit_rotated_ellipse_ransac(maxcnt.reshape(-1, 2), self.rng) if ransac_data is None: @@ -437,62 +1172,55 @@ class HSRAC_cls(object): # go to next loop pass + crop_start_time = timeit.default_timer() cx, cy, w, h, theta = ransac_data print(cx, cy) - if ( - w >= 2.1 * h - ): # new blink detection algo lmao this works pretty good actually + if w >= 2.1 * h: #new blink detection algo lmao this works pretty good actually print("RAN BLINK") - # return center_x, center_y, frame, frame, True + #return center_x, center_y, frame, frame, True - csy = frame.shape[0] - csx = frame.shape[1] + csx = frame.shape[0] + csy = frame.shape[1] + + #cx = center_x - (csx - cx) # we find the difference between the crop size and ransac point, and subtract from the center point from HSF + # cy = center_y - (csy - cy) + + cx = (cx - 20) + center_x + cy = (cy - 20) + center_y - # cx = center_x - (csx - cx) # we find the difference between the crop size and ransac point, and subtract from the center point from HSF - # cy = center_y - (csy - cy) - cx = clamp((cx - 20) + center_x, 0, csx) - cy = clamp((cy - 20) + center_y, 0, csy) cv_end_time = timeit.default_timer() if imshow_enable or save_video: cv2.drawContours(frame_gray, contours, -1, (255, 0, 0), 1) cv2.circle(frame_gray, (cx, cy), 2, (0, 0, 255), -1) # cx1, cy1, w1, h1, theta1 = fit_rotated_ellipse(maxcnt.reshape(-1, 2)) - cv2.ellipse( - frame_gray, - (cx, cy), - (w, h), - theta * 180.0 / np.pi, - 0.0, - 360.0, - (50, 250, 200), - 1, - ) - + cv2.ellipse(frame_gray, (cx, cy), (w, h), theta * 180.0 / np.pi, 0.0, 360.0, (50, 250, 200), 1, ) + except: pass - - # print(frame_gray.shape, thresh.shape) + + + # print(frame_gray.shape, thresh.shape) try: return cx, cy, thresh, frame, gray_frame except: return center_x, center_y, thresh, frame, gray_frame -class External_Run_HSRACS(object): - def __init__(self): - self.algo = HSRAC_cls() +class External_Run_HSRACS: - def run(self, current_image_gray): - self.algo.current_image_gray = current_image_gray - center_x, center_y, thresh, frame, gray_frame = self.algo.single_run() + hsrac = HSRAC_cls() + + def HSRACS(self): + External_Run_HSRACS.hsrac.current_image_gray = self.current_image_gray + center_x, center_y, thresh, frame, gray_frame = External_Run_HSRACS.hsrac.single_run() return center_x, center_y, thresh, frame, gray_frame -if __name__ == "__main__": +if __name__ == '__main__': hsrac = HSRAC_cls() hsrac.open_video(video_path) while hsrac.read_frame(): - _ = hsrac.single_run() + _ = hsrac.single_run() \ No newline at end of file diff --git a/EyeTrackApp/img_utils.py b/EyeTrackApp/img_utils.py deleted file mode 100644 index 288f04d..0000000 --- a/EyeTrackApp/img_utils.py +++ /dev/null @@ -1,12 +0,0 @@ -import cv2 - - -def safe_crop(img, x, y, x2, y2): - # The order of the arguments can be reconsidered. - img_h, img_w = img.shape[1::-1] - outimg = img[max(0, y) : min(img_h, y2), max(0, x) : min(img_w, x2)].copy() - reqsize_x, reqsize_y = abs(x2 - x), abs(y2 - y) - if outimg.shape[1::-1] != (reqsize_y, reqsize_x): - # If the size is different from the expected size (smaller by the amount that is out of range) - outimg = cv2.resize(outimg, (reqsize_x, reqsize_y)) - return outimg diff --git a/EyeTrackApp/ransac.py b/EyeTrackApp/ransac.py index 06d7c40..355600a 100644 --- a/EyeTrackApp/ransac.py +++ b/EyeTrackApp/ransac.py @@ -19,7 +19,7 @@ @@@@@@@@@@@@@@@@@ @@@@@@@@@@@@@( -RANSAC 3D By: Summer#2406 (Main Algorithm Engineer), Pupil Labs (pye3d), PallasNeko (Optimization) +RANSAC 3D By: Summer#2406 (Main Algorithm Engineer), Pupil Labs (pye3d), Sean.Denka (Optimization) Algorithm App Implimentations By: Prohurtz#0001, qdot (Inital App Creator) Copyright (c) 2022 EyeTrackVR <3 diff --git a/EyeTrackApp/time_utils.py b/EyeTrackApp/time_utils.py deleted file mode 100644 index ec46710..0000000 --- a/EyeTrackApp/time_utils.py +++ /dev/null @@ -1,171 +0,0 @@ -import functools -import math -import sys -import timeit - -def TimeitWrapper(*args, **kwargs): - """ - This decorator @TimeitWrapper() prints the function name and execution time in seconds. - :param args: - :param kwargs: - :return: - """ - - def decorator(function): - @functools.wraps(function) - def wrapper(*args, **kwargs): - start = timeit.default_timer() - results = function(*args, **kwargs) - end = timeit.default_timer() - print('{} execution time: {:.10f} s'.format(function.__name__, end - start)) - return results - - return wrapper - - return decorator - - -class TimeitResult(object): - """ - from https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 - - Object returned by the timeit magic with info about the run. - Contains the following attributes : - loops: (int) number of loops done per measurement - repeat: (int) number of times the measurement has been repeated - best: (float) best execution time / number - all_runs: (list of float) execution time of each run (in s) - """ - - def __init__(self, loops, repeat, best, worst, all_runs, precision): - self.loops = loops - self.repeat = repeat - self.best = best - self.worst = worst - self.all_runs = all_runs - self._precision = precision - self.timings = [dt / self.loops for dt in all_runs] - - @property - def average(self): - return math.fsum(self.timings) / len(self.timings) - - @property - def stdev(self): - mean = self.average - return (math.fsum([(x - mean) ** 2 for x in self.timings]) / len(self.timings)) ** 0.5 - - def __str__(self): - pm = '+-' - if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: - try: - u'\xb1'.encode(sys.stdout.encoding) - pm = u'\xb1' - except: - pass - return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( - pm=pm, - runs=self.repeat, - loops=self.loops, - loop_plural="" if self.loops == 1 else "s", - run_plural="" if self.repeat == 1 else "s", - mean=format_time(self.average, self._precision), - std=format_time(self.stdev, self._precision), - best=format_time(self.best, self._precision), - worst=format_time(self.worst, self._precision), - ) - - def _repr_pretty_(self, p, cycle): - unic = self.__str__() - p.text(u'') - - -class FPSResult(object): - """ - base https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L55 - """ - - def __init__(self, loops, repeat, best, worst, all_runs, precision): - self.loops = loops - self.repeat = repeat - self.best = 1 / best - self.worst = 1 / worst - self.all_runs = all_runs - self._precision = precision - self.fps = [1 / dt for dt in all_runs] - self.unit = "fps" - - @property - def average(self): - return math.fsum(self.fps) / len(self.fps) - - @property - def stdev(self): - mean = self.average - return (math.fsum([(x - mean) ** 2 for x in self.fps]) / len(self.fps)) ** 0.5 - - def __str__(self): - pm = '+-' - if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: - try: - u'\xb1'.encode(sys.stdout.encoding) - pm = u'\xb1' - except: - pass - return "min:{best} max:{worst} mean:{mean} {pm} {std} per loop (mean {pm} std. dev. of {runs} run{run_plural}, {loops:,} loop{loop_plural} each)".format( - pm=pm, - runs=self.repeat, - loops=self.loops, - loop_plural="" if self.loops == 1 else "s", - run_plural="" if self.repeat == 1 else "s", - mean="%.*g%s" % (self._precision, self.average, self.unit), - std="%.*g%s" % (self._precision, self.stdev, self.unit), - best="%.*g%s" % (self._precision, self.best, self.unit), - worst="%.*g%s" % (self._precision, self.worst, self.unit), - ) - - def _repr_pretty_(self, p, cycle): - unic = self.__str__() - p.text(u'') - - -def format_time(timespan, precision=3): - """ - https://github.com/ipython/ipython/blob/339c0d510a1f3cb2158dd8c6e7f4ac89aa4c89d8/IPython/core/magics/execution.py#L1473 - Formats the timespan in a human readable form - """ - - if timespan >= 60.0: - # we have more than a minute, format that in a human readable form - # Idea from http://snipplr.com/view/5713/ - parts = [("d", 60 * 60 * 24), ("h", 60 * 60), ("min", 60), ("s", 1)] - time = [] - leftover = timespan - for suffix, length in parts: - value = int(leftover / length) - if value > 0: - leftover = leftover % length - time.append(u'%s%s' % (str(value), suffix)) - if leftover < 1: - break - return " ".join(time) - - # Unfortunately the unicode 'micro' symbol can cause problems in - # certain terminals. - # See bug: https://bugs.launchpad.net/ipython/+bug/348466 - # Try to prevent crashes by being more secure than it needs to - # E.g. eclipse is able to print a µ, but has no sys.stdout.encoding set. - units = [u"s", u"ms", u'us', "ns"] # the save value - if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding: - try: - u'\xb5'.encode(sys.stdout.encoding) - units = [u"s", u"ms", u'\xb5s', "ns"] - except: - pass - scaling = [1, 1e3, 1e6, 1e9] - - if timespan > 0.0: - order = min(-int(math.floor(math.log10(timespan)) // 3), 3) - else: - order = 3 - return u"%.*g %s" % (precision, timespan * scaling[order], units[order]) \ No newline at end of file diff --git a/EyeTrackApp/utils.py b/EyeTrackApp/utils.py deleted file mode 100644 index 13931a7..0000000 --- a/EyeTrackApp/utils.py +++ /dev/null @@ -1,2 +0,0 @@ -def clamp(x, low, high): - return max(low, min(x, high)) \ No newline at end of file