somthin funky wunky with cropped image output or something?

This commit is contained in:
Prohurtz 2023-01-11 21:30:15 -06:00
parent b2ce947b24
commit d5c2270464
3 changed files with 817 additions and 218 deletions

View File

@ -239,7 +239,7 @@ class EyeProcessor:
def HSRACM(self):
cx, cy, thresh = External_Run.HSRACE(self)
cx, cy, thresh = External_Run.HSRACS(self)
if self.prev_x == None:
self.prev_x = cx
self.prev_y = cy
@ -257,7 +257,7 @@ class EyeProcessor:
# 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)
cx, cy, frame = External_Run_HSF.HSFS(self)
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, True)) #update app

View File

@ -1,35 +1,5 @@
'''
------------------------------------------------------------------------------------------------------
,@@@@@@
@@@@@@@@@@@ @@@
@@@@@@@@@@@@ @@@@@@@@@@@
@@@@@@@@@@@@@ @@@@@@@@@@@@@@
@@@@@@@/ ,@@@@@@@@@@@@@
/@@@@@@@@@@@@@@@ @@@@@@@@
@@@@@@@@@@@@@@@@@@@@@@@@ @@@@@
@@@@@@@@ @@@@@
,@@@ @@@@&
@@@@@@. @@@@
@@@ @@@@@@@@@/ @@@@@
,@@@. @@@@@@((@ @@@@(
//@@@ ,, @@@@ @@@@@
@@@( @@@@@@@
@@@ @ @@@@@@@@#
@@@@@@@@@@@@@@@@@
@@@@@@@@@@@@@(
HSR By: Sean.Denka (Optimization Wizard, Contributor), Summer#2406 (Main Algorithm Engineer)
Algorithm App Implimentations By: Prohurtz#0001, qdot (Inital App Creator)
Copyright (c) 2022 EyeTrackVR <3
------------------------------------------------------------------------------------------------------
'''
import functools
import math
import os
import sys
import timeit
from functools import lru_cache
@ -39,6 +9,8 @@ import numpy as np
# from line_profiler_pycharm import profile
video_path = "ezgif.com-gif-maker.avi"
imshow_enable = True
calc_print_enable = True
save_video = False
skip_autoradius = False
@ -50,6 +22,7 @@ lru_maxsize_vs = 64
# CV param
default_radius = 20
auto_radius_range = (default_radius - 10, default_radius + 10) # (10,30)
auto_radius_step = 1
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
@ -278,7 +251,7 @@ 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
@ -309,10 +282,15 @@ 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):
"""
:param imageshape: (height(row),width(col)). row==y,cal==x
:param xysteps: (x,y)
:param pad: int
@ -361,7 +339,6 @@ def get_hsf_empty_array(len_syx, frameint_x, frame_int_dtype, fcshape):
# @profile
def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
"""
:param frame_int:
:param kernel: hsf
:param step: (x,y)
@ -442,183 +419,438 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
return frame_conv, min_response, center
# @profile
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
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):
#global now_mode
#global response_list
#global radius_cand_list
#global response_max
# default_radius = 15
#frame = self.current_image_gray
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
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
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]
cvparam.radius = auto_radius_range[0]
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]]
cvparam.radius = auto_radius_range[1]
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(response_list, key=lambda x: x[1])[0]
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.
cvparam.radius = default_radius
now_mode = cv_mode[2] if not skip_blink_detect else cv_mode[3]
response_list = []
self.adj_comp_flag = True
return default_radius
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()
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:
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()
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(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 = []
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:
cvparam.radius = radius_cand_list.pop()
self.adj_comp_flag = False
return self.radius_cand_list.pop()
radius, pad, step, hsf = cvparam.get_rpsh()
def add_response(self, radius, response):
self.response_list.append((radius, response))
return None
# 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)
class Blink_Detector(object):
def __init__(self):
self.response_list = []
self.response_max = None
self.enable_detect_flg = False
self.quartile_1 = None
# 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)
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)
# 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)
# 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)
crop_start_time = timeit.default_timer()
# 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
self.response_max = float(quartile_3 + (iqr * 1.5))
# or
# self.response_max = quartile_3 + (iqr * 1.5)
# 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])
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:
# 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.")
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:
# 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)
x = center_x
y = center_y
# 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
# 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)
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)
#
# 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
# 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 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
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 = []
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 = 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": []}
def open_video(self, video_path):
# Temporary implementation to run
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
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():
return False
ret, frame = self.cap.read()
if ret:
# I have set it to grayscale (1ch) just in case, but if the frame is 1ch, this line can be commented out.
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]
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_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)
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
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 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)
elif self.now_modeo == self.cv_modeo[2]:
# 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(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]
else:
now_mode = cv_mode[1]
if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well.
print("Something's wrong.")
else:
orig_x, orig_y = center_x, center_y
if self.blink_detector.enable_detect_flg:
# If the average value of cropped_image is greater than response_max
# (i.e., if the cropimage is whitish
if self.blink_detector.detect(cv2.mean(cropped_image)[0]):
# blink
pass
else:
# 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)
# Define the center point and radius
center_xy = (center_x, center_y)
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 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
print('Kernel response:', response)
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 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:
self.now_modeo = self.cv_modeo[3]
elif skip_autoradius:
self.now_modeo = self.cv_modeo[2]
else:
self.now_modeo = self.cv_modeo[1]
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
class External_Run_HSF:
hsrac = HSRAC_cls()
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__':
hsrac = HSRAC_cls()
hsrac.open_video(video_path)
while hsrac.read_frame():
_ = hsrac.single_run()

View File

@ -7,6 +7,274 @@ from functools import lru_cache
import cv2
import numpy as np
#RANSAC
video_path = "demo2.mp4"
imshow_enable = False
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'<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
# from line_profiler_pycharm import profile
video_path = "ezgif.com-gif-maker.avi"
@ -703,7 +971,7 @@ class HSRAC_cls(object):
ret, frame = self.cap.read()
if ret:
# I have set it to grayscale (1ch) just in case, but if the frame is 1ch, this line can be commented out.
self.current_image_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
return True
return False
@ -790,21 +1058,21 @@ class HSRAC_cls(object):
# blink
pass
else:
pass
# if not self.center_correct.setup_comp:
# self.center_correct.init_array(gray_frame.shape, self.center_q1.quartile_1, radius)
#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)
# # Define the center point and radius
# center_xy = (center_x, center_y)
# 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]
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
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 imshow_enable or save_video:
cv2.circle(frame, (orig_x, orig_y), 10, (0, 0, 255), -1)
cv2.circle(frame, (orig_x, orig_y), 6, (0, 255, 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
@ -838,13 +1106,112 @@ class HSRAC_cls(object):
else:
self.now_modeo = self.cv_modeo[1]
return center_x, center_y, frame
#run ransac on the HSF crop\
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.
frame = cropped_image
# 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
detect_start_time = timeit.default_timer()
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
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
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, )
#img = newImage2[y1:y2, x1:x2]
except:
pass
try:
# print(radius)
return out_x, out_y, thresh
except:
return 0, 0, thresh
except:
return center_x, center_y, frame
# return center_x, center_y, frame
class External_Run:
hsrac = HSRAC_cls()
def HSRACE(self):
def HSRACS(self):
External_Run.hsrac.current_image_gray = self.current_image_gray
center_x, center_y, frame = External_Run.hsrac.single_run()
return center_x, center_y, frame
@ -886,7 +1253,7 @@ def HSRAC(self):
skip_autoradius = self.settings.gui_skip_autoradius
default_radius = self.settings.gui_HSF_radius
thresh_add = self.settings.gui_thresh_add
frame = self.current_image_gray
frame = frame
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
# adjustment of radius
@ -1085,7 +1452,7 @@ def HSRAC(self):
# 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
frame = frame
#img = newImage2[y1:y2, x1:x2]
#except:
# print('R F')
@ -1102,7 +1469,7 @@ def HSRAC(self):
yoff = prev_hsfy - prev_rany
return (xoff), (yoff), thresh
except:
self.current_image_gray = frame #cv2.resize(frame, (150, 150), interpolation = cv2.INTER_AREA)
frame = frame #cv2.resize(frame, (150, 150), interpolation = cv2.INTER_AREA)
xoff = prev_hsfx - 28
yoff = prev_hsfy - 28
print(prev_hsfx, prev_ranx)
@ -1137,7 +1504,7 @@ def HSRAC(self):
response_max = None
response_list = []
print("RESET HSRAC")
frame = self.current_image_gray
frame = frame
if now_mode == cv_mode[1]:
prev_res_len = len(response_list)
@ -1312,17 +1679,17 @@ def HSRAC(self):
out_x, out_y = cx, cy
cx, cy, w, h = int(cx), int(cy), int(w), int(h)
cv2.drawContours(self.current_image_gray, contours, -1, (255, 0, 0), 1)
cv2.circle(self.current_image_gray, (cx, cy), 2, (0, 0, 255), -1)
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(self.current_image_gray, (cx, cy), (w, h), theta * 180.0 / np.pi, 0.0, 360.0, (50, 250, 200), 1, )
cv2.ellipse(frame, (cx, cy), (w, h), theta * 180.0 / np.pi, 0.0, 360.0, (50, 250, 200), 1, )
#img = newImage2[y1:y2, x1:x2]
except:
pass
self.current_image_gray = frame
cv2.circle(self.current_image_gray, min_loc, 2, (0, 0, 255),
frame = frame
cv2.circle(frame, min_loc, 2, (0, 0, 255),
-1) # the point of the darkest area in the image
try:
# print(radius)
@ -1331,5 +1698,5 @@ def HSRAC(self):
except:
return 0, 0, thresh
except:
return center_x, center_y, self.current_image_gray
return center_x, center_y, frame
'''