-
Notifications
You must be signed in to change notification settings - Fork 575
/
face_reco_from_camera_ot.py
306 lines (249 loc) · 16.1 KB
/
face_reco_from_camera_ot.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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
# Copyright (C) 2018-2021 coneypo
# SPDX-License-Identifier: MIT
# Author: coneypo
# Blog: http://www.cnblogs.com/AdaminXie
# GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera
# Mail: [email protected]
# 利用 OT 人脸追踪, 进行人脸实时识别 / Real-time face detection and recognition via OT for multi faces
# 检测 -> 识别人脸, 新人脸出现 -> 不需要识别, 而是利用质心追踪来判断识别结果 / Do detection -> recognize face, new face -> not do re-recognition
# 人脸进行再识别需要花费大量时间, 这里用 OT 做跟踪 / Do re-recognition for multi faces will cost much time, OT will be used to instead it
import dlib
import numpy as np
import cv2
import os
import pandas as pd
import time
import logging
# Dlib 正向人脸检测器 / Use frontal face detector of Dlib
detector = dlib.get_frontal_face_detector()
# Dlib 人脸 landmark 特征点检测器 / Get face landmarks
predictor = dlib.shape_predictor('data/data_dlib/shape_predictor_68_face_landmarks.dat')
# Dlib Resnet 人脸识别模型, 提取 128D 的特征矢量 / Use Dlib resnet50 model to get 128D face descriptor
face_reco_model = dlib.face_recognition_model_v1("data/data_dlib/dlib_face_recognition_resnet_model_v1.dat")
class Face_Recognizer:
def __init__(self):
self.font = cv2.FONT_ITALIC
# FPS
self.frame_time = 0
self.frame_start_time = 0
self.fps = 0
self.fps_show = 0
self.start_time = time.time()
# cnt for frame
self.frame_cnt = 0
# 用来存放所有录入人脸特征的数组 / Save the features of faces in the database
self.face_features_known_list = []
# 存储录入人脸名字 / Save the name of faces in the database
self.face_name_known_list = []
# 用来存储上一帧和当前帧 ROI 的质心坐标 / List to save centroid positions of ROI in frame N-1 and N
self.last_frame_face_centroid_list = []
self.current_frame_face_centroid_list = []
# 用来存储上一帧和当前帧检测出目标的名字 / List to save names of objects in frame N-1 and N
self.last_frame_face_name_list = []
self.current_frame_face_name_list = []
# 上一帧和当前帧中人脸数的计数器 / cnt for faces in frame N-1 and N
self.last_frame_face_cnt = 0
self.current_frame_face_cnt = 0
# 用来存放进行识别时候对比的欧氏距离 / Save the e-distance for faceX when recognizing
self.current_frame_face_X_e_distance_list = []
# 存储当前摄像头中捕获到的所有人脸的坐标名字 / Save the positions and names of current faces captured
self.current_frame_face_position_list = []
# 存储当前摄像头中捕获到的人脸特征 / Save the features of people in current frame
self.current_frame_face_feature_list = []
# e distance between centroid of ROI in last and current frame
self.last_current_frame_centroid_e_distance = 0
# 控制再识别的后续帧数 / Reclassify after 'reclassify_interval' frames
# 如果识别出 "unknown" 的脸, 将在 reclassify_interval_cnt 计数到 reclassify_interval 后, 对于人脸进行重新识别
self.reclassify_interval_cnt = 0
self.reclassify_interval = 10
# 从 "features_all.csv" 读取录入人脸特征 / Get known faces from "features_all.csv"
def get_face_database(self):
if os.path.exists("data/features_all.csv"):
path_features_known_csv = "data/features_all.csv"
csv_rd = pd.read_csv(path_features_known_csv, header=None)
for i in range(csv_rd.shape[0]):
features_someone_arr = []
self.face_name_known_list.append(csv_rd.iloc[i][0])
for j in range(1, 129):
if csv_rd.iloc[i][j] == '':
features_someone_arr.append('0')
else:
features_someone_arr.append(csv_rd.iloc[i][j])
self.face_features_known_list.append(features_someone_arr)
logging.info("Faces in Database： %d", len(self.face_features_known_list))
return 1
else:
logging.warning("'features_all.csv' not found!")
logging.warning("Please run 'get_faces_from_camera.py' "
"and 'features_extraction_to_csv.py' before 'face_reco_from_camera.py'")
return 0
def update_fps(self):
now = time.time()
# 每秒刷新 fps / Refresh fps per second
if str(self.start_time).split(".")[0] != str(now).split(".")[0]:
self.fps_show = self.fps
self.start_time = now
self.frame_time = now - self.frame_start_time
self.fps = 1.0 / self.frame_time
self.frame_start_time = now
@staticmethod
# 计算两个128D向量间的欧式距离 / Compute the e-distance between two 128D features
def return_euclidean_distance(feature_1, feature_2):
feature_1 = np.array(feature_1)
feature_2 = np.array(feature_2)
dist = np.sqrt(np.sum(np.square(feature_1 - feature_2)))
return dist
# 使用质心追踪来识别人脸 / Use centroid tracker to link face_x in current frame with person_x in last frame
def centroid_tracker(self):
for i in range(len(self.current_frame_face_centroid_list)):
e_distance_current_frame_person_x_list = []
# 对于当前帧中的人脸1, 和上一帧中的 人脸1/2/3/4/.. 进行欧氏距离计算 / For object 1 in current_frame, compute e-distance with object 1/2/3/4/... in last frame
for j in range(len(self.last_frame_face_centroid_list)):
self.last_current_frame_centroid_e_distance = self.return_euclidean_distance(
self.current_frame_face_centroid_list[i], self.last_frame_face_centroid_list[j])
e_distance_current_frame_person_x_list.append(
self.last_current_frame_centroid_e_distance)
last_frame_num = e_distance_current_frame_person_x_list.index(
min(e_distance_current_frame_person_x_list))
self.current_frame_face_name_list[i] = self.last_frame_face_name_list[last_frame_num]
# 生成的 cv2 window 上面添加说明文字 / putText on cv2 window
def draw_note(self, img_rd):
# 添加说明 / Add some info on windows
cv2.putText(img_rd, "Face Recognizer with OT", (20, 40), self.font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Frame: " + str(self.frame_cnt), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps.__round__(2)), (20, 130), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Faces: " + str(self.current_frame_face_cnt), (20, 160), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
for i in range(len(self.current_frame_face_name_list)):
img_rd = cv2.putText(img_rd, "Face_" + str(i + 1), tuple(
[int(self.current_frame_face_centroid_list[i][0]), int(self.current_frame_face_centroid_list[i][1])]),
self.font,
0.8, (255, 190, 0),
1,
cv2.LINE_AA)
# 处理获取的视频流, 进行人脸识别 / Face detection and recognition wit OT from input video stream
def process(self, stream):
# 1. 读取存放所有人脸特征的 csv / Get faces known from "features.all.csv"
if self.get_face_database():
while stream.isOpened():
self.frame_cnt += 1
logging.debug("Frame " + str(self.frame_cnt) + " starts")
flag, img_rd = stream.read()
kk = cv2.waitKey(1)
# 2. 检测人脸 / Detect faces for frame X
faces = detector(img_rd, 0)
# 3. 更新人脸计数器 / Update cnt for faces in frames
self.last_frame_face_cnt = self.current_frame_face_cnt
self.current_frame_face_cnt = len(faces)
# 4. 更新上一帧中的人脸列表 / Update the face name list in last frame
self.last_frame_face_name_list = self.current_frame_face_name_list[:]
# 5. 更新上一帧和当前帧的质心列表 / update frame centroid list
self.last_frame_face_centroid_list = self.current_frame_face_centroid_list
self.current_frame_face_centroid_list = []
# 6.1 如果当前帧和上一帧人脸数没有变化 / if cnt not changes
if (self.current_frame_face_cnt == self.last_frame_face_cnt) and (
self.reclassify_interval_cnt != self.reclassify_interval):
logging.debug("scene 1: 当前帧和上一帧相比没有发生人脸数变化 / No face cnt changes in this frame!!!")
self.current_frame_face_position_list = []
if "unknown" in self.current_frame_face_name_list:
logging.debug(" 有未知人脸, 开始进行 reclassify_interval_cnt 计数")
self.reclassify_interval_cnt += 1
if self.current_frame_face_cnt != 0:
for k, d in enumerate(faces):
self.current_frame_face_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
self.current_frame_face_centroid_list.append(
[int(faces[k].left() + faces[k].right()) / 2,
int(faces[k].top() + faces[k].bottom()) / 2])
img_rd = cv2.rectangle(img_rd,
tuple([d.left(), d.top()]),
tuple([d.right(), d.bottom()]),
(255, 255, 255), 2)
# 如果当前帧中有多个人脸, 使用质心追踪 / Multi-faces in current frame, use centroid-tracker to track
if self.current_frame_face_cnt != 1:
self.centroid_tracker()
for i in range(self.current_frame_face_cnt):
# 6.2 Write names under ROI
img_rd = cv2.putText(img_rd, self.current_frame_face_name_list[i],
self.current_frame_face_position_list[i], self.font, 0.8, (0, 255, 255), 1,
cv2.LINE_AA)
self.draw_note(img_rd)
# 6.2 如果当前帧和上一帧人脸数发生变化 / If cnt of faces changes, 0->1 or 1->0 or ...
else:
logging.debug("scene 2: 当前帧和上一帧相比人脸数发生变化 / Faces cnt changes in this frame")
self.current_frame_face_position_list = []
self.current_frame_face_X_e_distance_list = []
self.current_frame_face_feature_list = []
self.reclassify_interval_cnt = 0
# 6.2.1 人脸数减少 / Face cnt decreases: 1->0, 2->1, ...
if self.current_frame_face_cnt == 0:
logging.debug(" scene 2.1 人脸消失, 当前帧中没有人脸 / No faces in this frame!!!")
# clear list of names and features
self.current_frame_face_name_list = []
# 6.2.2 人脸数增加 / Face cnt increase: 0->1, 0->2, ..., 1->2, ...
else:
logging.debug(" scene 2.2 出现人脸, 进行人脸识别 / Get faces in this frame and do face recognition")
self.current_frame_face_name_list = []
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_face_feature_list.append(
face_reco_model.compute_face_descriptor(img_rd, shape))
self.current_frame_face_name_list.append("unknown")
# 6.2.2.1 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
logging.debug(" For face %d in current frame:", k + 1)
self.current_frame_face_centroid_list.append(
[int(faces[k].left() + faces[k].right()) / 2,
int(faces[k].top() + faces[k].bottom()) / 2])
self.current_frame_face_X_e_distance_list = []
# 6.2.2.2 每个捕获人脸的名字坐标 / Positions of faces captured
self.current_frame_face_position_list.append(tuple(
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
# 6.2.2.3 对于某张人脸, 遍历所有存储的人脸特征
# For every faces detected, compare the faces in the database
for i in range(len(self.face_features_known_list)):
# 如果 q 数据不为空
if str(self.face_features_known_list[i][0]) != '0.0':
e_distance_tmp = self.return_euclidean_distance(
self.current_frame_face_feature_list[k],
self.face_features_known_list[i])
logging.debug(" with person %d, the e-distance: %f", i + 1, e_distance_tmp)
self.current_frame_face_X_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
self.current_frame_face_X_e_distance_list.append(999999999)
# 6.2.2.4 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
similar_person_num = self.current_frame_face_X_e_distance_list.index(
min(self.current_frame_face_X_e_distance_list))
if min(self.current_frame_face_X_e_distance_list) < 0.4:
self.current_frame_face_name_list[k] = self.face_name_known_list[similar_person_num]
logging.debug(" Face recognition result: %s",
self.face_name_known_list[similar_person_num])
else:
logging.debug(" Face recognition result: Unknown person")
# 7. 生成的窗口添加说明文字 / Add note on cv2 window
self.draw_note(img_rd)
# cv2.imwrite("debug/debug_" + str(self.frame_cnt) + ".png", img_rd) # Dump current frame image if needed
# 8. 按下 'q' 键退出 / Press 'q' to exit
if kk == ord('q'):
break
self.update_fps()
cv2.namedWindow("camera", 1)
cv2.imshow("camera", img_rd)
logging.debug("Frame ends\n\n")
def run(self):
# cap = cv2.VideoCapture("video.mp4") # Get video stream from video file
cap = cv2.VideoCapture(0) # Get video stream from camera
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main():
# logging.basicConfig(level=logging.DEBUG) # Set log level to 'logging.DEBUG' to print debug info of every frame
logging.basicConfig(level=logging.INFO)
Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run()
if __name__ == '__main__':
main()