Merge remote-tracking branch 'origin/fix_safecrop' into fix_safecrop

# Conflicts:
#	EyeTrackApp/eye_processor.py
This commit is contained in:
PallasNeko 2023-02-02 01:23:16 +09:00
commit ec83c3831f
3 changed files with 1193 additions and 342 deletions

View File

@ -4,9 +4,11 @@ from functools import lru_cache
import cv2 import cv2
import numpy as np import numpy as np
from utils.misc_utils import clamp from utils.misc_utils import clamp
from utils.img_utils import safe_crop from utils.img_utils import safe_crop
# from line_profiler_pycharm import profile # from line_profiler_pycharm import profile
video_path = "ezgif.com-gif-maker.avi" video_path = "ezgif.com-gif-maker.avi"
@ -27,6 +29,180 @@ blink_init_frames = 60 * 3 # 60fps*3sec,Number of blink statistical frames
# step==(x,y) # step==(x,y)
default_step = (5, 5) # bigger the steps,lower the processing time! ofc acc also takes an impact 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'<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])
class CvParameters: class CvParameters:
# It may be a little slower because a dict named "self" is read for each function call. # It may be a little slower because a dict named "self" is read for each function call.
@ -73,6 +249,7 @@ class CvParameters:
class HaarSurroundFeature: class HaarSurroundFeature:
def __init__(self, r_inner, r_outer=None, val=None): def __init__(self, r_inner, r_outer=None, val=None):
if r_outer is None: if r_outer is None:
r_outer = r_inner * 3 r_outer = r_inner * 3
@ -97,14 +274,11 @@ class HaarSurroundFeature:
def get_kernel(self): def get_kernel(self):
# Defined here, but not yet used? # Defined here, but not yet used?
# Create a kernel filled with the value of self.val_out # Create a kernel filled with the value of self.val_out
kernel = ( kernel = np.ones(shape=(2 * self.r_out - 1, 2 * self.r_out - 1), dtype=np.float64) * self.val_out
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 # Set the values of the inner area of the kernel using array slicing
start = self.r_out - self.r_in start = (self.r_out - self.r_in)
end = self.r_out + self.r_in - 1 end = (self.r_out + self.r_in - 1)
kernel[start:end, start:end] = self.val_in kernel[start:end, start:end] = self.val_in
return kernel return kernel
@ -161,13 +335,7 @@ def get_hsf_empty_array(len_syx, frameint_x, frame_int_dtype, fcshape):
response_list = np.empty(len_syx, dtype=np.float64) response_list = np.empty(len_syx, dtype=np.float64)
frame_conv = np.zeros(shape=fcshape[0], dtype=np.uint8) frame_conv = np.zeros(shape=fcshape[0], dtype=np.uint8)
frame_conv_stride = frame_conv[::fcshape[1], ::fcshape[2]] frame_conv_stride = frame_conv[::fcshape[1], ::fcshape[2]]
return ( return (inner_sum, outer_sum), p_temp, (p00, p11, p01, p10), response_list, (frame_conv, frame_conv_stride)
(inner_sum, outer_sum),
p_temp,
(p00, p11, p01, p10),
response_list,
(frame_conv, frame_conv_stride),
)
# @profile # @profile
@ -188,9 +356,8 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
r_in = kernel.r_in r_in = kernel.r_in
len_sx, len_sy = len(xy_steps_list[0]), len(xy_steps_list[1]) 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( inout_sum, p_temp, p_list, response_list, frameconvlist = get_hsf_empty_array((len_sy, len_sx), col + 1,
(len_sy, len_sx), col + 1, frame_int.dtype, (f_shape, y_step, x_step) frame_int.dtype, (f_shape, y_step, x_step))
)
inner_sum, outer_sum = inout_sum inner_sum, outer_sum = inout_sum
p00, p11, p01, p10 = p_list p00, p11, p01, p10 = p_list
frame_conv, frame_conv_stride = frameconvlist frame_conv, frame_conv_stride = frameconvlist
@ -200,18 +367,10 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
y_rin_p = xy_steps_list[1] + r_in y_rin_p = xy_steps_list[1] + r_in
x_rin_p = xy_steps_list[0] + r_in x_rin_p = xy_steps_list[0] + r_in
# xx==(y,x),m==MINUS,p==PLUS, ex: mm==(y-,x-) # xx==(y,x),m==MINUS,p==PLUS, ex: mm==(y-,x-)
inarr_mm = frame_int[ 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]
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_mp = frame_int[ 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]
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 # == inarr_mm + inarr_pp - inarr_mp - inarr_pm
inner_sum[:, :] = inarr_mm inner_sum[:, :] = inarr_mm
@ -253,10 +412,7 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
# min_response, max_val, min_loc, max_loc = cv2.minMaxLoc(response_list) # min_response, max_val, min_loc, max_loc = cv2.minMaxLoc(response_list)
min_response, _, min_loc, _ = cv2.minMaxLoc(response_list) min_response, _, min_loc, _ = cv2.minMaxLoc(response_list)
center = ( center = ((xy_steps_list[0][min_loc[0]] - padding), (xy_steps_list[1][min_loc[1]] - padding))
(xy_steps_list[0][min_loc[0]] - padding),
(xy_steps_list[1][min_loc[1]] - padding),
)
frame_conv_stride[:, :] = response_list frame_conv_stride[:, :] = response_list
# or # or
@ -265,7 +421,7 @@ def conv_int(frame_int, kernel, xy_step, padding, xy_steps_list):
return frame_conv, min_response, center return frame_conv, min_response, center
class AutoRadiusCalc(object): class Auto_Radius_Calc(object):
def __init__(self): def __init__(self):
self.response_list = [] self.response_list = []
self.radius_cand_list = [] self.radius_cand_list = []
@ -297,35 +453,21 @@ class AutoRadiusCalc(object):
else: else:
self.left_item = self.response_list[0] self.left_item = self.response_list[0]
self.right_item = self.response_list[2] self.right_item = self.response_list[2]
self.radius_cand_list = [ self.radius_cand_list = [i for i in range(self.left_item[0], self.right_item[0] + auto_radius_step, auto_radius_step)]
i
for i in range(
self.left_item[0],
self.right_item[0] + auto_radius_step,
auto_radius_step,
)
]
self.left_index = 0 self.left_index = 0
self.right_index = len(self.radius_cand_list) - 1 self.right_index = len(self.radius_cand_list) - 1
self.radius_middle_index = (self.left_index + self.right_index) // 2 self.radius_middle_index = (self.left_index + self.right_index) // 2
self.adj_comp_flag = False self.adj_comp_flag = False
return self.radius_cand_list[self.radius_middle_index] return self.radius_cand_list[self.radius_middle_index]
else: else:
if ( if self.left_index <= self.right_index and self.left_index != self.radius_middle_index:
self.left_index <= self.right_index if (self.left_item[1] + self.response_list[-1][1]) < (self.right_item[1] + self.response_list[-1][1]):
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_item = self.response_list[-1]
self.right_index = self.radius_middle_index - 1 self.right_index = self.radius_middle_index - 1
self.radius_middle_index = (self.left_index + self.right_index) // 2 self.radius_middle_index = (self.left_index + self.right_index) // 2
self.adj_comp_flag = False self.adj_comp_flag = False
return self.radius_cand_list[self.radius_middle_index] return self.radius_cand_list[self.radius_middle_index]
if (self.left_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.right_item[1] + self.response_list[-1][1]
):
self.left_item = self.response_list[-1] self.left_item = self.response_list[-1]
self.left_index = self.radius_middle_index + 1 self.left_index = self.radius_middle_index + 1
self.radius_middle_index = (self.left_index + self.right_index) // 2 self.radius_middle_index = (self.left_index + self.right_index) // 2
@ -359,21 +501,11 @@ class AutoRadiusCalc(object):
self.adj_comp_flag = True self.adj_comp_flag = True
return default_radius return default_radius
elif sort_res[0] == auto_radius_range[0]: elif sort_res[0] == auto_radius_range[0]:
self.radius_cand_list = [ self.radius_cand_list = [i for i in range(auto_radius_range[0], default_radius, auto_radius_step)][1:]
i
for i in range(
auto_radius_range[0], default_radius, auto_radius_step
)
][1:]
self.adj_comp_flag = False self.adj_comp_flag = False
return self.radius_cand_list.pop() return self.radius_cand_list.pop()
else: else:
self.radius_cand_list = [ self.radius_cand_list = [i for i in range(default_radius, auto_radius_range[1], auto_radius_step)][1:]
i
for i in range(
default_radius, auto_radius_range[1], auto_radius_step
)
][1:]
self.adj_comp_flag = False self.adj_comp_flag = False
return self.radius_cand_list.pop() return self.radius_cand_list.pop()
else: else:
@ -392,7 +524,7 @@ class AutoRadiusCalc(object):
return None return None
class BlinkDetector(object): class Blink_Detector(object):
def __init__(self): def __init__(self):
self.response_list = [] self.response_list = []
self.response_max = None self.response_max = None
@ -447,9 +579,7 @@ class CenterCorrection(object):
self.frame_mask = None self.frame_mask = None
self.frame_bin = None self.frame_bin = None
self.frame_final = None self.frame_final = None
self.morph_kernel = cv2.getStructuringElement( self.morph_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (kernel_size, kernel_size))
cv2.MORPH_RECT, (kernel_size, kernel_size)
)
self.morph_kernel2 = np.ones((3, 3)) self.morph_kernel2 = np.ones((3, 3))
self.hist_index = np.arange(256) self.hist_index = np.arange(256)
self.hist = np.empty((256, 1)) self.hist = np.empty((256, 1))
@ -479,27 +609,17 @@ class CenterCorrection(object):
cv2.normalize(self.hist, self.hist_norm, alpha=100.0, norm_type=cv2.NORM_L1) cv2.normalize(self.hist, self.hist_norm, alpha=100.0, norm_type=cv2.NORM_L1)
hist_per = self.hist_norm.cumsum() hist_per = self.hist_norm.cumsum()
hist_index_list = self.hist_index[hist_per >= self.hist_thr] hist_index_list = self.hist_index[hist_per >= self.hist_thr]
frame_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)
hist_index_list[0]
if len(hist_index_list)
else np.percentile(cv2.bitwise_or(255 - self.frame_mask, gray_frame), 4)
)
# bottleneck # bottleneck
self.frame_bin = cv2.threshold(gray_frame, frame_thr, 1, cv2.THRESH_BINARY_INV)[ self.frame_bin = cv2.threshold(gray_frame, frame_thr, 1, cv2.THRESH_BINARY_INV)[1]
1
]
cropped_x, cropped_y, cropped_w, cropped_h = cv2.boundingRect(self.frame_bin) 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) self.frame_final = cv2.bitwise_and(self.frame_bin, self.frame_mask)
# bottleneck # bottleneck
self.frame_final = cv2.morphologyEx( self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_CLOSE, self.morph_kernel)
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_OPEN, self.morph_kernel
)
if (cropped_h, cropped_w) == self.frame_shape: if (cropped_h, cropped_w) == self.frame_shape:
# Not detected. # Not detected.
@ -509,30 +629,17 @@ class CenterCorrection(object):
base_y = cropped_y + cropped_h // 2 base_y = cropped_y + cropped_h // 2
if self.frame_final[base_y, base_x] != 1: if self.frame_final[base_y, base_x] != 1:
if self.frame_final[center_y, center_x] != 1: if self.frame_final[center_y, center_x] != 1:
self.frame_final = cv2.morphologyEx( self.frame_final = cv2.morphologyEx(self.frame_final, cv2.MORPH_DILATE, self.morph_kernel2, iterations=3)
self.frame_final,
cv2.MORPH_DILATE,
self.morph_kernel2,
iterations=3,
)
else: else:
base_x, base_y = center_x, center_y base_x, base_y = center_x, center_y
contours, _ = cv2.findContours( contours, _ = cv2.findContours(self.frame_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
self.frame_final, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE
)
contours_box = [cv2.boundingRect(cnt) for cnt in contours] contours_box = [cv2.boundingRect(cnt) for cnt in contours]
contours_dist = np.array( 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): if len(contours_box):
cropped_x2, cropped_y2, cropped_w2, cropped_h2 = contours_box[ cropped_x2, cropped_y2, cropped_w2, cropped_h2 = contours_box[contours_dist.argmin()]
contours_dist.argmin()
]
x = cropped_x2 + cropped_w2 // 2 x = cropped_x2 + cropped_w2 // 2
y = cropped_y2 + cropped_h2 // 2 y = cropped_y2 + cropped_h2 // 2
else: else:
@ -547,13 +654,8 @@ class CenterCorrection(object):
# out_x = center_x if abs(x - center_x) > radius else x # 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_y = center_y if abs(y - center_y) > radius else y
out_x, out_y = orig_x, orig_y out_x, out_y = orig_x, orig_y
if ( if gray_frame[int(max(y - 5, 0)):int(min(y + 5, self.frame_shape[0])),
gray_frame[ int(max(x - 5, 0)):int(min(x + 5, self.frame_shape[1]))].min() < self.quartile_1:
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_x = x
out_y = y out_y = y
@ -565,8 +667,7 @@ class CenterCorrection(object):
return out_x, out_y return out_x, out_y
# temporary name class HSRAC_cls(object):
class HSF_cls(object):
def __init__(self): 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. # I'd like to take into account things like print, end_time - start_time processing time, etc., but it's too much trouble.
@ -580,20 +681,14 @@ class HSF_cls(object):
self.cv_modeo = ["first_frame", "radius_adjust", "blink_adjust", "normal"] self.cv_modeo = ["first_frame", "radius_adjust", "blink_adjust", "normal"]
self.now_modeo = self.cv_modeo[0] self.now_modeo = self.cv_modeo[0]
self.auto_radius_calc = AutoRadiusCalc() self.auto_radius_calc = Auto_Radius_Calc()
self.blink_detector = BlinkDetector() self.blink_detector = Blink_Detector()
self.center_q1 = BlinkDetector() self.center_q1 = Blink_Detector()
self.center_correct = CenterCorrection() self.center_correct = CenterCorrection()
self.cap = None self.cap = None
self.timedict = { self.timedict = {"to_gray": [], "int_img": [], "conv_int": [], "crop": [], "total_cv": []}
"to_gray": [],
"int_img": [],
"conv_int": [],
"crop": [],
"total_cv": [],
}
def open_video(self, video_path): def open_video(self, video_path):
# Temporary implementation to run # Temporary implementation to run
@ -617,10 +712,12 @@ class HSF_cls(object):
def single_run(self): def single_run(self):
# Temporary implementation to run # Temporary implementation to run
# default_radius = 14
## default_radius = 14
# cropbox=[] # debug code # cropbox=[] # debug code
frame = self.current_image_gray frame = self.current_image_gray
if self.now_modeo == self.cv_modeo[1]: if self.now_modeo == self.cv_modeo[1]:
# adjustment of radius # adjustment of radius
@ -633,9 +730,7 @@ class HSF_cls(object):
self.cvparam.radius = self.auto_radius_calc.get_radius() self.cvparam.radius = self.auto_radius_calc.get_radius()
if self.auto_radius_calc.adj_comp_flag: if self.auto_radius_calc.adj_comp_flag:
self.now_modeo = ( self.now_modeo = self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3]
self.cv_modeo[2] if not skip_blink_detect else self.cv_modeo[3]
)
radius, pad, step, hsf = self.cvparam.get_rpsh() radius, pad, step, hsf = self.cvparam.get_rpsh()
@ -648,17 +743,13 @@ class HSF_cls(object):
# Calculate the integral image of the frame # Calculate the integral image of the frame
int_start_time = timeit.default_timer() 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. # BORDER_CONSTANT is faster than BORDER_REPLICATE There seems to be almost no negative impact when BORDER_CONSTANT is used.
frame_pad = cv2.copyMakeBorder( frame_pad = cv2.copyMakeBorder(gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT)
gray_frame, pad, pad, pad, pad, cv2.BORDER_CONSTANT
)
frame_int = cv2.integral(frame_pad) frame_int = cv2.integral(frame_pad)
self.timedict["int_img"].append(timeit.default_timer() - int_start_time) self.timedict["int_img"].append(timeit.default_timer() - int_start_time)
# Convolve the feature with the integral image # Convolve the feature with the integral image
conv_int_start_time = timeit.default_timer() conv_int_start_time = timeit.default_timer()
xy_step = frameint_get_xy_step( xy_step = frameint_get_xy_step(frame_int.shape, step, pad, start_offset=None, end_offset=None)
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) 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) self.timedict["conv_int"].append(timeit.default_timer() - conv_int_start_time)
@ -671,11 +762,13 @@ class HSF_cls(object):
lower_y = center_y - radius lower_y = center_y - radius
# Crop the image using the calculated bounds # Crop the image using the calculated bounds
cropped_image = safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y) cropped_image = safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y)
# cropbox = [clamp(val, 0, gray_frame.shape[i]) for i, val in # cropbox = [clamp(val, 0, gray_frame.shape[i]) for i, val in
# zip([1, 0, 1, 0], [lower_x, lower_y, upper_x, upper_y])] # debug code # zip([1, 0, 1, 0], [lower_x, lower_y, upper_x, upper_y])] # debug code
if self.now_modeo == self.cv_modeo[0] or self.now_modeo == self.cv_modeo[1]: 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 # If mode is first_frame or radius_adjust, record current radius and response
self.auto_radius_calc.add_response(radius, response) self.auto_radius_calc.add_response(radius, response)
@ -688,12 +781,14 @@ class HSF_cls(object):
lower_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 upper_y = center_y + self.center_correct.center_q1_radius
lower_y = center_y - self.center_correct.center_q1_radius lower_y = center_y - self.center_correct.center_q1_radius
self.center_q1.add_response( self.center_q1.add_response(
cv2.mean(safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y,keepsize=False))[ cv2.mean(safe_crop(gray_frame, lower_x, lower_y, upper_x, upper_y,keepsize=False))[
0 0
] ]
) )
else: else:
self.blink_detector.calc_thresh() self.blink_detector.calc_thresh()
@ -743,6 +838,7 @@ class HSF_cls(object):
# if imshow_enable or save_video: # if imshow_enable or save_video:
# cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1) # cv2.circle(frame, (orig_x, orig_y), 6, (0, 0, 255), -1)
# cv2.circle(frame, (center_x, center_y), 3, (255, 0, 0), -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 # 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 # https://stackoverflow.com/questions/42771110/fastest-way-to-left-cycle-a-numpy-array-like-pop-push-for-a-queue
@ -756,10 +852,7 @@ class HSF_cls(object):
# print('Pixel position:', center_xy) # print('Pixel position:', center_xy)
if imshow_enable: if imshow_enable:
if ( if self.now_modeo != self.cv_modeo[0] and self.now_modeo != self.cv_modeo[1]:
self.now_modeo != self.cv_modeo[0]
and self.now_modeo != self.cv_modeo[1]
):
if 0 in cropped_image.shape: if 0 in cropped_image.shape:
# If shape contains 0, it is not detected well. # If shape contains 0, it is not detected well.
pass pass
@ -778,12 +871,11 @@ class HSF_cls(object):
else: else:
self.now_modeo = self.cv_modeo[1] self.now_modeo = self.cv_modeo[1]
# debug code # debug code
# return center_x,center_y,cropbox,frame # return center_x,center_y,cropbox,frame
return center_x, center_y, frame return center_x, center_y, frame
class External_Run_HSF(object): class External_Run_HSF(object):
def __init__(self): def __init__(self):
self.algo = HSF_cls() self.algo = HSF_cls()

File diff suppressed because it is too large Load Diff

View File

@ -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) Algorithm App Implimentations By: Prohurtz#0001, qdot (Inital App Creator)
Copyright (c) 2022 EyeTrackVR <3 Copyright (c) 2022 EyeTrackVR <3