nightly update

fall back to HSF in HSRAC is not correct. TODO
This commit is contained in:
Prohurtz 2023-01-02 15:36:29 -08:00
parent 1ecbde4f7b
commit db1883929a
6 changed files with 863 additions and 361 deletions

View File

@ -45,6 +45,7 @@ class EyeTrackSettingsConfig(BaseModel):
gui_RANSAC3DP: int = 2
gui_HSFP: int = 3
gui_BLOBP: int = 4
gui_skip_autoradius: bool = True
class EyeTrackConfig(BaseModel):
version: int = 1

View File

@ -153,25 +153,8 @@ class EyeProcessor:
self.failed = 0
self.response_list = [] #This might not be correct.
#HSF
self.cv_mode = ["first_frame", "radius_adjust", "init", "normal"]
self.now_mode = self.cv_mode[0]
self.cvparam = CvParameters(default_radius, default_step)
self.skip_blink_detect = False
self.default_step = (5, 5) # bigger the steps,lower the processing time! ofc acc also takes an impact
# self.default_step==(x,y)
self.radius_cand_list = []
self.blink_init_frames = 60 * 3
prev_max_size = 60 * 3 # 60fps*3sec
# response_min=0
self.response_max = None
self.auto_radius_range = (self.settings.gui_HSF_radius - 10, self.settings.gui_HSF_radius + 10)
#blink
self.max_ints = []
self.max_int = 0
@ -179,6 +162,8 @@ class EyeProcessor:
self.frames = 0
self.blinkvalue = False
self.prev_x = None
self.prev_y = None
@ -209,7 +194,7 @@ class EyeProcessor:
self.previous_image = self.current_image
self.previous_rotation = self.config.rotation_angle
except:
print("E")
pass
def capture_crop_rotate_image(self):
# Get our current frame
@ -255,12 +240,22 @@ class EyeProcessor:
def HSRACM(self):
cx, cy, thresh = HSRAC(self)
if self.prev_x == None:
self.prev_x = cx
self.prev_y = cy
#print(self.prev_x, self.prev_y, cx, cy)
# if (cx - self.prev_x) <= 45 and (cy - self.prev_y) <= 45 :
# self.prev_x = cx
# self.prev_y = cy
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
self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, False)) #update app
else:
self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, self.blinkvalue))
self.blinkvalue = False
self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, out_x, out_y, 0, False))
# else:
# print("EYE MOVED TOO FAST")
# self.output_images_and_update(thresh, EyeInformation(InformationOrigin.HSRAC, 0, 0, 0, False))
def HSFM(self):
cx, cy, frame = HSF(self)
out_x, out_y = cal_osc(self, cx, cy)
@ -294,31 +289,24 @@ class EyeProcessor:
def ALGOSELECT(self):
print(self.failed, self.firstalgo)
if self.failed == 0 and self.firstalgo != None:
print('first')
self.firstalgo()
if self.failed == 0 and self.firstalgo != None:
self.firstalgo()
else:
self.failed = self.failed + 1
if self.failed == 1 and self.secondalgo != None:
print('2nd') #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 != None:
print('3rd')
self.thirdalgo()
else:
self.failed = self.failed + 1
if self.failed == 3 and self.fourthalgo != None:
print('4th')
self.fourthalgo()
else:
self.failed = 0 # we have reached last possible algo and it is disabled, move to first algo
@ -352,7 +340,6 @@ class EyeProcessor:
self.fourthalgo = self.RANSAC3DM
if self.settings.gui_HSRAC == True and self.settings.gui_HSRACP == 1:
print("HERE")
self.firstalgo = self.HSRACM
elif self.settings.gui_HSRAC and self.settings.gui_HSRACP == 2:
self.secondalgo = self.HSRACM
@ -370,12 +357,6 @@ class EyeProcessor:
elif self.settings.gui_BLOB and self.settings.gui_BLOBP == 4:
self.fourthalgo = self.BLOBM
if self.settings.gui_HSRACP == '1':
print("HERE")
print(self.settings.gui_HSRACP, self.settings.gui_HSRAC, self.firstalgo)
f = True
while True:
# f = True
@ -391,7 +372,7 @@ class EyeProcessor:
return
continue
# If our ROI configuration has changed, reset our model and detector
if (self.camera_model is None

View File

@ -27,15 +27,22 @@ Copyright (c) 2022 EyeTrackVR <3
'''
import cv2
import numpy as np
import timeit
from functools import lru_cache
import os
import sys
import functools
import math
#HSF \/
import os
import sys
import timeit
from functools import lru_cache
import cv2
import numpy as np
# from line_profiler_pycharm import profile
calc_print_enable = True
save_video = False
skip_autoradius = False
skip_blink_detect = False
# cache param
lru_maxsize_vvs = 16
@ -46,7 +53,6 @@ auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
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
response_list = []
"""
Attention.
@ -303,12 +309,6 @@ class HaarSurroundFeature:
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):
"""
@ -430,154 +430,179 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
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(self.response_list)
# 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[:, :] = self.response_list.astype(np.uint8)
# frame_conv_stride[:, :] = response_list.astype(np.uint8)
return frame_conv, min_response, center
# @profile
timedict = {"to_gray": [], "int_img": [], "conv_int": [], "crop": [], "total_cv": []}
# 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
main_start_time = timeit.default_timer()
rng = np.random.default_rng()
cvparam = CvParameters(default_radius, default_step)
cv_mode = ["first_frame", "radius_adjust", "init", "normal"]
now_mode = cv_mode[0]
radius_cand_list = []
# response_min=0
response_max = None
response_list = []
def HSF(self):
frame = self.current_image_gray
if self.now_mode == self.cv_mode[1]:
prev_res_len = len(self.response_list)
# adjustment of radius
if prev_res_len == 1:
# len==1==self.response_list==[self.settings.gui_HSF_radius]
self.cvparam.radius = self.auto_radius_range[0]
elif prev_res_len == 2:
# len==2==self.response_list==[self.settings.gui_HSF_radius, self.auto_radius_range[0]]
self.cvparam.radius = self.auto_radius_range[1]
elif prev_res_len == 3:
# len==3==self.response_list==[self.settings.gui_HSF_radius,self.auto_radius_range[0],self.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] == self.settings.gui_HSF_radius:
# If the default value is best, change self.now_mode to init after setting radius to the default value.
self.cvparam.radius = self.settings.gui_HSF_radius
self.now_mode = self.cv_mode[2] if not self.skip_blink_detect else self.cv_mode[3]
self.response_list = []
elif sort_res[0] == self.auto_radius_range[0]:
self.radius_cand_list = [i for i in range(self.auto_radius_range[0], self.settings.gui_HSF_radius, self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = self.radius_cand_list.pop()
else:
self.radius_cand_list = [i for i in range(self.settings.gui_HSF_radius, self.auto_radius_range[1], self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = self.radius_cand_list.pop()
global now_mode
global response_list
global radius_cand_list
global response_max
# default_radius = 15
frame = self.current_image_gray
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
# adjustment of radius
if prev_res_len == 1:
# len==1==response_list==[default_radius]
cvparam.radius = auto_radius_range[0]
elif prev_res_len == 2:
# len==2==response_list==[default_radius, auto_radius_range[0]]
cvparam.radius = 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(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.
cvparam.radius = default_radius
now_mode = cv_mode[2] if not skip_blink_detect else cv_mode[3]
response_list = []
elif sort_res[0] == auto_radius_range[0]:
radius_cand_list = [i for i in range(auto_radius_range[0], default_radius, default_step[0])][1:]
# default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than default_step
cvparam.radius = radius_cand_list.pop()
else:
# Try the contents of the self.radius_cand_list in order until the self.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.cvparam.radius = sort_res[0]
self.now_mode = self.cv_mode[2] if not self.skip_blink_detect else self.cv_mode[3]
self.response_list = []
else:
self.cvparam.radius = self.radius_cand_list.pop()
radius, pad, step, hsf = self.cvparam.get_rpsh()
# For measuring processing time of image processing
cv_start_time = timeit.default_timer()
gray_frame = frame
# 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_int = cv2.integral(frame_pad)
# 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)
frame_conv, response, center_xy = conv_int(frame_int, hsf, step, pad, xy_step)
crop_start_time = timeit.default_timer()
# Define the center point and radius
center_x, center_y = center_xy
upper_x = center_x + 25 #TODO make this a setting
lower_x = center_x - 25
upper_y = center_y + 25
lower_y = center_y - 25
# Crop the image using the calculated bounds
cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] # y is 50px, x is 45? why?
if self.now_mode == self.cv_mode[0] or self.now_mode == self.cv_mode[1]:
# If mode is first_frame or radius_adjust, record current radius and response
self.response_list.append((radius, response))
elif self.now_mode == self.cv_mode[2]:
# Statistics for blink detection
if len(self.response_list) < self.blink_init_frames:
# Record the average value of cropped_image
self.response_list.append(cv2.mean(cropped_image)[0])
else:
# Calculate self.response_max by computing interquartile range, IQR
# Change self.cv_mode to normal
self.response_list = np.array(self.response_list)
# 25%,75%
# This value may need to be adjusted depending on the environment.
quartile_1, quartile_3 = np.percentile(self.response_list, [25, 75])
iqr = quartile_3 - quartile_1
# response_min = quartile_1 - (iqr * 1.5)
self.response_max = quartile_3 + (iqr * 1.5)
self.now_mode = self.cv_mode[3]
radius_cand_list = [i for i in range(default_radius, auto_radius_range[1], default_step[0])][1:]
# default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than default_step
cvparam.radius = radius_cand_list.pop()
else:
if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well.
print("[WARN] HSF: Something's wrong.")
# 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(radius_cand_list) == 0:
sort_res = sorted(response_list, key=lambda x: x[1])[0]
cvparam.radius = sort_res[0]
now_mode = cv_mode[2] if not skip_blink_detect else cv_mode[3]
response_list = []
else:
# If the average value of cropped_image is greater than self.response_max
# (i.e., if the cropimage is whitish
if self.response_max is not None and cv2.mean(cropped_image)[0] > self.response_max:
# blink
cv2.circle(frame, (center_x, center_y), 10, (0, 0, 255), -1)
# If you want to update self.response_max. it may be more cost-effective to rewrite self.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
cv2.circle(frame, (center_x, center_y), 10, (0, 0, 255), -1)
# print(center_x, center_y)
if self.now_mode != self.cv_mode[0] and self.now_mode != self.cv_mode[1]:
if cropped_image.size < 400:
pass
cvparam.radius = radius_cand_list.pop()
if self.now_mode == self.cv_mode[0]:
self.now_mode = self.cv_mode[1]
radius, pad, step, hsf = cvparam.get_rpsh()
# For measuring processing time of image processing
cv_start_time = timeit.default_timer()
gray_frame = frame
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_int = cv2.integral(frame_pad)
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)
frame_conv, response, center_xy = conv_int(frame_int, hsf, step, pad, xy_step)
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
upper_x = center_x + radius
lower_x = center_x - radius
upper_y = center_y + radius
lower_y = center_y - radius
# Crop the image using the calculated bounds
cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x]
if now_mode == cv_mode[0] or now_mode == cv_mode[1]:
# If mode is first_frame or radius_adjust, record current radius and response
response_list.append((radius, response))
elif now_mode == cv_mode[2]:
# Statistics for blink detection
if len(response_list) < blink_init_frames:
# Record the average value of cropped_image
response_list.append(cv2.mean(cropped_image)[0])
else:
# Calculate response_max by computing interquartile range, IQR
# Change cv_mode to normal
response_list = np.array(response_list)
# 25%,75%
# This value may need to be adjusted depending on the environment.
quartile_1, quartile_3 = np.percentile(response_list, [25, 75])
iqr = quartile_3 - quartile_1
# response_min = quartile_1 - (iqr * 1.5)
response_max = quartile_3 + (iqr * 1.5)
now_mode = cv_mode[3]
else:
if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well.
print("Something's wrong.")
else:
# If the average value of cropped_image is greater than response_max
# (i.e., if the cropimage is whitish
if response_max is not None and cv2.mean(cropped_image)[0] > response_max:
# blink
cv2.circle(frame, (center_x, center_y), 10, (0, 0, 255), -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()
timedict["crop"].append(cv_end_time - crop_start_time)
timedict["total_cv"].append(cv_end_time - cv_start_time)
# 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)
if now_mode == cv_mode[0]:
# Moving from first_frame to the next mode
if skip_autoradius and skip_blink_detect:
now_mode = cv_mode[3]
response_list = []
elif skip_autoradius:
now_mode = cv_mode[2]
response_list = []
else:
now_mode = cv_mode[1]
try:
self.failed = 0
return center_x, center_y, frame
except:
self.failed = self.failed + 1
return 0, 0, frame
try:
self.failed = 0
return center_x, center_y, frame
except:
self.failed = self.failed + 1
return 0, 0, frame
#self.output_images_and_update(thresh, EyeInformation(InformationOrigin.FAILURE, 0, 0, 0, False))
# return
#self.output_images_and_update(larger_threshold,EyeInformation(InformationOrigin.HSF, out_x, out_y, 0, False),)
# return
#self.output_images_and_update(larger_threshold, EyeInformation(InformationOrigin.HSF, 0, 0, 0, True))

View File

@ -1,25 +1,298 @@
import cv2
import numpy as np
import timeit
from functools import lru_cache
import os
import sys
import functools
import math
import os
import sys
import timeit
from functools import lru_cache
#HSF \/
import cv2
import numpy as np
# from line_profiler_pycharm import profile
#RANSACAHA
thresh_add = 20
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'<TimeitResult : ' + unic + 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'<FPSResult : ' + unic + 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):
"""
There is no need to make this process a function, since making the process a function will slow it down a little by calling it.
The results may be slightly different from the lambda version due to calculation errors derived from float types, but the calculation results are virtually the same.
a = 1.0,b = P[0],c = P[1],d = P[2],e = P[3],f = P[4]
:param data:
:param y: np.c_[d, e, a, c, b]
:param f: f == P[4, 0]
:return: this_return == np.array([ellipse_model(x, y) for (x, y) in data ])
"""
return data.dot(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
# 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)
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))
# 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))
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)
# @profile
def fit_rotated_ellipse(data, P):
a = 1.0
b = P[0]
c = P[1]
d = P[2]
e = P[3]
f = P[4]
# The cost of trigonometric functions is high.
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
b_tcs = b * theta_cos * theta_sin
# Do the calculation only once
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_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)
# HSF
calc_print_enable = True
save_video = False
skip_autoradius = True
skip_blink_detect = False
# cache param
lru_maxsize_vvs = 16
lru_maxsize_vs = 64
# CV param
#default_radius = 15
#auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
default_radius = 10
auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
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
response_list = []
"""
Attention.
@ -205,7 +478,6 @@ 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
@ -277,12 +549,6 @@ class HaarSurroundFeature:
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):
"""
@ -404,170 +670,388 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
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(self.response_list)
# 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[:, :] = self.response_list.astype(np.uint8)
# frame_conv_stride[:, :] = response_list.astype(np.uint8)
return frame_conv, min_response, center
#RANSAC \/
def ellipse_model(data, y, f):
"""
There is no need to make this process a function, since making the process a function will slow it down a little by calling it.
The results may be slightly different from the lambda version due to calculation errors derived from float types, but the calculation results are virtually the same.
a = 1.0,b = P[0],c = P[1],d = P[2],e = P[3],f = P[4]
:param data:
:param y: np.c_[d, e, a, c, b]
:param f: f == P[4, 0]
:return: this_return == np.array([ellipse_model(x, y) for (x, y) in data ])
"""
return data.dot(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
# 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)
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))
# 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))
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)
# @profile
def fit_rotated_ellipse(data, P):
a = 1.0
b = P[0]
c = P[1]
d = P[2]
e = P[3]
f = P[4]
# The cost of trigonometric functions is high.
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
b_tcs = b * theta_cos * theta_sin
# Do the calculation only once
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_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)
timedict = {"to_gray": [], "int_img": [], "conv_int": [], "crop": [], "total_cv": []}
# 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
main_start_time = timeit.default_timer()
rng = np.random.default_rng()
cvparam = CvParameters(default_radius, default_step)
cv_mode = ["first_frame", "radius_adjust", "init", "normal"]
now_mode = cv_mode[0]
radius_cand_list = []
# response_min=0
response_max = None
response_list = []
prev_hsfx = 0
prev_hsfy = 0
prev_ranx = 0
prev_rany = 0
def HSRAC(self):
default_radius = self.settings.gui_HSF_radius
auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
frame = self.current_image_gray
if self.now_mode == self.cv_mode[1]:
global now_mode
global response_list
global radius_cand_list
global response_max
global skip_autoradius
global default_radius
global prev_rany
global prev_ranx
global prev_hsfy
global prev_hsfx
skip_autoradius = self.settings.gui_skip_autoradius
default_radius = self.settings.gui_HSF_radius
frame = self.current_image_gray
prev_res_len = len(self.response_list)
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
# adjustment of radius
if prev_res_len == 1:
# len==1==self.response_list==[default_radius]
self.cvparam.radius = self.auto_radius_range[0]
# len==1==response_list==[default_radius]
cvparam.radius = auto_radius_range[0]
elif prev_res_len == 2:
# len==2==self.response_list==[default_radius, self.auto_radius_range[0]]
self.cvparam.radius = self.auto_radius_range[1]
# len==2==response_list==[default_radius, auto_radius_range[0]]
cvparam.radius = auto_radius_range[1]
elif prev_res_len == 3:
# len==3==self.response_list==[default_radius,self.auto_radius_range[0],self.auto_radius_range[1]]
sort_res = sorted(self.response_list, key=lambda x: x[1])[0]
# len==3==response_list==[default_radius,auto_radius_range[0],auto_radius_range[1]]
sort_res = sorted(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 self.now_mode to init after setting radius to the default value.
self.cvparam.radius = default_radius
self.now_mode = self.cv_mode[2] if not self.skip_blink_detect else self.cv_mode[3]
self.response_list = []
elif sort_res[0] == self.auto_radius_range[0]:
self.radius_cand_list = [i for i in range(self.auto_radius_range[0], default_radius, self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = self.radius_cand_list.pop()
# If the default value is best, change now_mode to init after setting radius to the default value.
cvparam.radius = default_radius
now_mode = cv_mode[2] if not skip_blink_detect else cv_mode[3]
response_list = []
elif sort_res[0] == auto_radius_range[0]:
radius_cand_list = [i for i in range(auto_radius_range[0], default_radius, default_step[0])][1:]
# default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than default_step
cvparam.radius = radius_cand_list.pop()
else:
self.radius_cand_list = [i for i in range(default_radius, self.auto_radius_range[1], self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = self.radius_cand_list.pop()
radius_cand_list = [i for i in range(default_radius, auto_radius_range[1], default_step[0])][1:]
# default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than default_step
cvparam.radius = radius_cand_list.pop()
else:
# Try the contents of the self.radius_cand_list in order until the self.radius_cand_list runs out
# 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.cvparam.radius = sort_res[0]
self.now_mode = self.cv_mode[2] if not self.skip_blink_detect else self.cv_mode[3]
self.response_list = []
if len(radius_cand_list) == 0:
sort_res = sorted(response_list, key=lambda x: x[1])[0]
cvparam.radius = sort_res[0]
now_mode = cv_mode[2] if not skip_blink_detect else cv_mode[3]
response_list = []
else:
self.cvparam.radius = self.radius_cand_list.pop()
cvparam.radius = radius_cand_list.pop()
radius, pad, step, hsf = cvparam.get_rpsh()
# For measuring processing time of image processing
cv_start_time = timeit.default_timer()
gray_frame = frame
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_int = cv2.integral(frame_pad)
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)
frame_conv, response, center_xy = conv_int(frame_int, hsf, step, pad, xy_step)
timedict["conv_int"].append(timeit.default_timer() - conv_int_start_time)
# Define the center point and radius
center_x, center_y = center_xy
upper_x = center_x + 20
lower_x = center_x - 20
upper_y = center_y + 20
lower_y = center_y - 20
# Crop the image using the calculated bounds
cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x]
frame = cropped_image
if now_mode == cv_mode[0] or now_mode == cv_mode[1]:
# If mode is first_frame or radius_adjust, record current radius and response
response_list.append((radius, response))
elif now_mode == cv_mode[2]:
# Statistics for blink detection
if len(response_list) < blink_init_frames:
# Record the average value of cropped_image
response_list.append(cv2.mean(cropped_image)[0])
else:
# Calculate response_max by computing interquartile range, IQR
# Change cv_mode to normal
response_list = np.array(response_list)
# 25%,75%
# This value may need to be adjusted depending on the environment.
quartile_1, quartile_3 = np.percentile(response_list, [25, 75])
iqr = quartile_3 - quartile_1
# response_min = quartile_1 - (iqr * 1.5)
response_max = quartile_3 + (iqr * 1.5)
now_mode = cv_mode[3]
else:
if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well.
print("Something's wrong.")
else:
# If the average value of cropped_image is greater than response_max
# (i.e., if the cropimage is whitish
if response_max is not None and cv2.mean(cropped_image)[0] > response_max:
# blink
self.blinkvalue = True
print("HSF BLINK")
# 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
# 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)
if now_mode == cv_mode[0]:
# Moving from first_frame to the next mode
if skip_autoradius and skip_blink_detect:
now_mode = cv_mode[3]
response_list = []
elif skip_autoradius:
now_mode = cv_mode[2]
response_list = []
else:
now_mode = cv_mode[1]
#run ransac on the HSF crop\
frame = cropped_image
# try:
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
thresh_add = 10
rng = np.random.default_rng()
f = False
# Convert the image to grayscale, and set up thresholding. Thresholds here are basically a
# low-pass filter that will set any pixel < the threshold value to 0. Thresholding is user
# configurable in this utility as we're dealing with variable lighting amounts/placement, as
# well as camera positioning and lensing. Therefore everyone's cutoff may be different.
#
# The goal of thresholding settings is to make sure we can ONLY see the pupil. This is why we
# crop the image earlier; it gives us less possible dark area to get confused about in the
# next step.
# For measuring processing time of image processing
# Crop first to reduce the amount of data to process.
#frame = frame[0:len(frame) - 5, :]
# 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.
try:
frame = cv2.GaussianBlur(frame, (5, 5), 0)
except:
pass
# 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)
maxloc0_hf, maxloc1_hf = int(0.5 * max_loc[0]), int(0.5 * max_loc[1])
# crop 15% sqare around min_loc
# frame = frame[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, threshold_value, 255, cv2.THRESH_BINARY)
try:
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
closing = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, kernel)
th_frame = 255 - closing
except:
# I want to eliminate try here because try tends to be slow in execution.
th_frame = 255 - frame
contours, _ = cv2.findContours(th_frame, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
hull = []
# This way is faster than contours[i]
# But maybe this one is faster. hull = [cv2.convexHull(cnt, False) for cnt in contours]
for cnt in contours:
hull.append(cv2.convexHull(cnt, False))
if not hull:
# 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), rng)
if ransac_data is None:
# ransac_data is None==maxcnt.shape[0]<sample_num
# go to next loop
print("NODATYA")
pass
crop_start_time = timeit.default_timer()
cx, cy, w, h, theta = ransac_data
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)
out_x, out_y = cx, cy
prev_hsfx = center_x
prev_hsfy = center_y
prev_ranx = cx
prev_rany = cy
cx, cy, w, h = int(cx), int(cy), int(w), int(h)
cv2.drawContours(frame, contours, -1, (255, 0, 0), 1)
cv2.circle(frame, (cx, cy), 2, (0, 0, 255), -1)
# cx1, cy1, w1, h1, theta1 = fit_rotated_ellipse(maxcnt.reshape(-1, 2))
cv2.ellipse(frame, (cx, cy), (w, h), theta * 180.0 / np.pi, 0.0, 360.0, (50, 250, 200), 1, )
cv2.circle(frame, min_loc, 2, (0, 0, 255),-1) # the point of the darkest area in the image
self.current_image_gray = frame
#img = newImage2[y1:y2, x1:x2]
#except:
# print('R F')
# pass
try:
# print(radius)
return out_x, out_y, thresh
except:
xoff = prev_hsfx - prev_ranx
yoff = prev_hsfy - prev_rany
return (center_x + xoff), (center_y + yoff), thresh
except:
self.current_image_gray = frame #cv2.resize(frame, (150, 150), interpolation = cv2.INTER_AREA)
xoff = prev_hsfx - prev_ranx
yoff = prev_hsfy - prev_rany
return (center_x + xoff), (center_y + yoff), thresh
'''
try:
self.failed = 0
cv2.circle(frame, (center_x, center_y), 10, (0, 0, 255), -1)
return center_x, center_y, frame
except:
self.failed = self.failed + 1
return 0, 0, frame
'''
'''
def HSRAC(self):
global default_radius
global auto_radius_range
global response_list
global radius_cand_list
global response_max
global now_mode
global cv_mode
default_radius = int(self.settings.gui_HSF_radius)
auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
print(default_radius, cv_mode, now_mode, radius_cand_list, response_max )
if self.calibration_frame_counter == 0: # if reset triggered, reset all values
now_mode = cv_mode[0]
radius_cand_list = []
# response_min=0
response_max = None
response_list = []
print("RESET HSRAC")
frame = self.current_image_gray
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
# adjustment of radius
if prev_res_len == 1:
# len==1==response_list==[default_radius]
self.cvparam.radius = self.auto_radius_range[0]
elif prev_res_len == 2:
# len==2==response_list==[default_radius, self.auto_radius_range[0]]
self.cvparam.radius = self.auto_radius_range[1]
elif prev_res_len == 3:
# len==3==response_list==[default_radius,self.auto_radius_range[0],self.auto_radius_range[1]]
sort_res = sorted(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.cvparam.radius = default_radius
now_mode = cv_mode[2] if not self.skip_blink_detect else cv_mode[3]
response_list = []
elif sort_res[0] == self.auto_radius_range[0]:
radius_cand_list = [i for i in range(self.auto_radius_range[0], default_radius, self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = radius_cand_list.pop()
else:
radius_cand_list = [i for i in range(default_radius, self.auto_radius_range[1], self.default_step[0])][1:]
# self.default_step is defined separately for xy, but radius is shared by xy, so it may be buggy
# It should be no problem to set it to anything other than self.default_step
self.cvparam.radius = 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(radius_cand_list) == 0:
sort_res = sorted(response_list, key=lambda x: x[1])[0]
self.cvparam.radius = sort_res[0]
now_mode = cv_mode[2] if not self.skip_blink_detect else cv_mode[3]
response_list = []
else:
self.cvparam.radius = radius_cand_list.pop()
radius, pad, step, hsf = self.cvparam.get_rpsh()
@ -593,37 +1077,37 @@ def HSRAC(self):
# Crop the image using the calculated bounds
cropped_image = gray_frame[lower_y:upper_y, lower_x:upper_x] # y is 50px, x is 45? why?
if self.now_mode == self.cv_mode[0] or self.now_mode == self.cv_mode[1]:
if now_mode == cv_mode[0] or now_mode == cv_mode[1]:
# If mode is first_frame or radius_adjust, record current radius and response
self.response_list.append((radius, response))
elif self.now_mode == self.cv_mode[2]:
response_list.append((radius, response))
elif now_mode == cv_mode[2]:
# Statistics for blink detection
if len(self.response_list) < self.blink_init_frames:
if len(response_list) < self.blink_init_frames:
# Record the average value of cropped_image
self.response_list.append(cv2.mean(cropped_image)[0])
response_list.append(cv2.mean(cropped_image)[0])
else:
# Calculate self.response_max by computing interquartile range, IQR
# Change self.cv_mode to normal
self.response_list = np.array(self.response_list)
# Calculate response_max by computing interquartile range, IQR
# Change cv_mode to normal
response_list = np.array(response_list)
# 25%,75%
# This value may need to be adjusted depending on the environment.
quartile_1, quartile_3 = np.percentile(self.response_list, [25, 75])
quartile_1, quartile_3 = np.percentile(response_list, [25, 75])
iqr = quartile_3 - quartile_1
# response_min = quartile_1 - (iqr * 1.5)
self.response_max = quartile_3 + (iqr * 1.5)
self.now_mode = self.cv_mode[3]
response_max = quartile_3 + (iqr * 1.5)
now_mode = cv_mode[3]
else:
if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well.
print("Something's wrong.")
else:
# If the average value of cropped_image is greater than self.response_max
# If the average value of cropped_image is greater than response_max
# (i.e., if the cropimage is whitish
if self.response_max is not None and cv2.mean(cropped_image)[0] > self.response_max:
if response_max is not None and cv2.mean(cropped_image)[0] > response_max:
# blink
cv2.circle(frame, (center_x, center_y), 10, (0, 0, 255), -1)
# If you want to update self.response_max. it may be more cost-effective to rewrite self.response_list in the following way
# 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
except:
@ -652,27 +1136,27 @@ def HSRAC(self):
# 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)
frame = cv2.GaussianBlur(frame, (5, 5), 0)
# 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)
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(frame)
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 = frame[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)
_, thresh = cv2.threshold(frame, threshold_value, 255, cv2.THRESH_BINARY)
try:
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
closing = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, kernel)
th_frame = 255 - closing
except:
# I want to eliminate try here because try tends to be slow in execution.
th_frame = 255 - frame_gray
th_frame = 255 - frame
detect_start_time = timeit.default_timer()
@ -737,3 +1221,4 @@ def HSRAC(self):
'''

View File

@ -12,9 +12,6 @@ def cal_osc(self, cx, cy):
self.calibration_frame_counter = None
self.xoff = cx
self.yoff = cy
self.now_mode = self.cv_mode[0]
self.response_list = []
self.response_max = 0
if sys.platform.startswith("win"):
PlaySound('Audio/compleated.wav', SND_FILENAME | SND_ASYNC)
elif self.calibration_frame_counter != None:

View File

@ -32,7 +32,7 @@ class SettingsWidget:
self.gui_min_cutoff = f"-MINCUTOFF{widget_id}-"
self.gui_eye_falloff = f"-EYEFALLOFF{widget_id}-"
self.gui_blink_sync = f"-BLINKSYNC{widget_id}-"
self.gui_skip_autoradius = f"-SKIPAUTORADIUS{widget_id}-"
self.gui_HSRACP = f"-HSRACP{widget_id}-"
self.gui_RANSAC3DP = f"-RANSAC3DP{widget_id}-"
self.gui_HSFP = f"-HSFP{widget_id}-"
@ -177,7 +177,15 @@ class SettingsWidget:
),
],
[sg.Text("HSF Radius:", background_color='#424042'),
[sg.Checkbox(
"HSF: Skip Auto Radius",
default=self.config.gui_skip_autoradius,
key=self.gui_skip_autoradius,
background_color='#424042',
tooltip = "To gain more control and possibly better tracking quality of HSF, please disable auto radius to enable manual adjustment.",
),
sg.Text("HSF Radius:", background_color='#424042'),
sg.Slider(
range=(1, 50),
default_value=self.config.gui_HSF_radius,
@ -398,6 +406,11 @@ class SettingsWidget:
self.config.gui_HSRAC = values[self.gui_HSRAC]
changed = True
if self.config.gui_skip_autoradius != values[self.gui_skip_autoradius]:
self.config.gui_skip_autoradius = values[self.gui_skip_autoradius]
changed = True
if self.config.gui_BLINK != values[self.gui_BLINK]:
self.config.gui_BLINK = values[self.gui_BLINK]
changed = True