forked from Linzaer/Face-Track-Detect-Extract
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstart.py
147 lines (126 loc) · 6.96 KB
/
start.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import argparse
import os
import align.detect_face as detect_face
import cv2
import numpy as np
import tensorflow as tf
from lib.face_utils import judge_side_face
from lib.utils import Logger, mkdir
from project_root_dir import project_dir
from src.sort import Sort
logger = Logger()
def main():
global colours, img_size
args = parse_args()
root_dir = args.root_dir
output_path = args.output_path
display = args.display
mkdir(output_path)
# for disp
if display:
colours = np.random.rand(32, 3)
# init tracker
tracker = Sort() # create instance of the SORT tracker
logger.info('Start track and extract......')
with tf.Graph().as_default():
with tf.Session(config=tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True), log_device_placement=False)) as sess:
pnet, rnet, onet = detect_face.create_mtcnn(sess, os.path.join(project_dir, "align"))
margin = 40 # if the face is big in your video ,you can set it bigger for tracking easiler
minsize = 40 # minimum size of face for mtcnn to detect
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
frame_interval = 3 # interval how many frames to make a detection,you need to keep a balance between performance and fluency
scale_rate = 0.9 # if set it smaller will make input frames smaller
show_rate = 0.8 # if set it smaller will dispaly smaller frames
for filename in os.listdir(root_dir):
logger.info('All files:{}'.format(filename))
for filename in os.listdir(root_dir):
suffix = filename.split('.')[1]
if suffix != 'mp4' and suffix != 'avi': # you can specify more video formats if you need
continue
video_name = os.path.join(root_dir, filename)
directoryname = os.path.join(output_path, filename.split('.')[0])
logger.info('Video_name:{}'.format(video_name))
cam = cv2.VideoCapture(video_name)
c = 0
while True:
final_faces = []
addtional_attribute_list = []
ret, frame = cam.read()
if not ret:
logger.warning("ret false")
break
if frame is None:
logger.warning("frame drop")
break
frame = cv2.resize(frame, (0, 0), fx=scale_rate, fy=scale_rate)
r_g_b_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
if c % frame_interval == 0:
img_size = np.asarray(frame.shape)[0:2]
faces, points = detect_face.detect_face(r_g_b_frame, minsize, pnet, rnet, onet, threshold, factor)
face_sums = faces.shape[0]
if face_sums > 0:
face_list = []
for i, item in enumerate(faces):
f = round(faces[i, 4], 6)
if f > 0.99:
det = np.squeeze(faces[i, 0:4])
# face rectangle
det[0] = np.maximum(det[0] - margin, 0)
det[1] = np.maximum(det[1] - margin, 0)
det[2] = np.minimum(det[2] + margin, img_size[1])
det[3] = np.minimum(det[3] + margin, img_size[0])
face_list.append(item)
# face cropped
bb = np.array(det, dtype=np.int32)
frame_copy = frame.copy()
cropped = frame_copy[bb[1]:bb[3], bb[0]:bb[2], :]
# use 5 face landmarks to judge the face is front or side
squeeze_points = np.squeeze(points[:, i])
tolist = squeeze_points.tolist()
facial_landmarks = []
for j in range(5):
item = [tolist[j], tolist[(j + 5)]]
facial_landmarks.append(item)
if args.face_landmarks:
for (x, y) in facial_landmarks:
cv2.circle(frame_copy, (int(x), int(y)), 3, (0, 255, 0), -1)
dist_rate, high_ratio_variance, width_rate = judge_side_face(
np.array(facial_landmarks))
# face addtional attribute(index 0:face score; index 1:0 represents front face and 1 for side face )
item_list = [cropped, faces[i, 4], dist_rate, high_ratio_variance, width_rate]
addtional_attribute_list.append(item_list)
final_faces = np.array(face_list)
trackers = tracker.update(final_faces, img_size, directoryname, addtional_attribute_list, r_g_b_frame)
c += 1
for d in trackers:
if display:
d = d.astype(np.int32)
cv2.rectangle(frame, (d[0], d[1]), (d[2], d[3]), colours[d[4] % 32, :] * 255, 5)
cv2.putText(frame, 'ID : %d' % (d[4]), (d[0] - 10, d[1] - 10), cv2.FONT_HERSHEY_SIMPLEX,
0.75,
colours[d[4] % 32, :] * 255, 2)
if final_faces != []:
cv2.putText(frame, 'DETECTOR', (5, 45), cv2.FONT_HERSHEY_SIMPLEX, 0.75,
(1, 1, 1), 2)
if display:
frame = cv2.resize(frame, (0, 0), fx=show_rate, fy=show_rate)
cv2.imshow("Frame", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser()
parser.add_argument("root_dir", type=str,
help='Path to the data directory containing aligned your face patches.')
parser.add_argument('--output_path', type=str,
help='Path to save face',
default='facepics')
parser.add_argument('--display', type=bool,
help='Display or not', default=True)
parser.add_argument('--face_landmarks', type=bool,
help='draw 5 face landmarks on extracted face or not ', default=False)
args = parser.parse_args()
return args
if __name__ == '__main__':
main()