-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathvideo.py
197 lines (144 loc) · 5.34 KB
/
video.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
# coding=utf-8
from ctypes import *
import math
import random
import cv2
import time
from PIL import Image
def sample(probs):
s = sum(probs)
probs = [a / s for a in probs]
r = random.uniform(0, 1)
for i in range(len(probs)):
r = r - probs[i]
if r <= 0:
return i
return len(probs) - 1
def c_array(ctype, values):
arr = (ctype * len(values))()
arr[:] = values
return arr
class BOX(Structure):
_fields_ = [("x", c_float),
("y", c_float),
("w", c_float),
("h", c_float)]
class DETECTION(Structure):
_fields_ = [("bbox", BOX),
("classes", c_int),
("prob", POINTER(c_float)),
("mask", POINTER(c_float)),
("objectness", c_float),
("sort_class", c_int)]
class IMAGE(Structure):
_fields_ = [("w", c_int),
("h", c_int),
("c", c_int),
("data", POINTER(c_float))]
class METADATA(Structure):
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
# lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
lib = CDLL("/home/gjw/darknet-pjreddie/libdarknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
lib.network_height.restype = c_int
predict = lib.network_predict
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
set_gpu = lib.cuda_set_device
set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
make_image.restype = IMAGE
get_network_boxes = lib.get_network_boxes
get_network_boxes.argtypes = [c_void_p, c_int, c_int, c_float, c_float, POINTER(c_int), c_int, POINTER(c_int)]
get_network_boxes.restype = POINTER(DETECTION)
make_network_boxes = lib.make_network_boxes
make_network_boxes.argtypes = [c_void_p]
make_network_boxes.restype = POINTER(DETECTION)
free_detections = lib.free_detections
free_detections.argtypes = [POINTER(DETECTION), c_int]
free_ptrs = lib.free_ptrs
free_ptrs.argtypes = [POINTER(c_void_p), c_int]
network_predict = lib.network_predict
network_predict.argtypes = [c_void_p, POINTER(c_float)]
reset_rnn = lib.reset_rnn
reset_rnn.argtypes = [c_void_p]
load_net = lib.load_network
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
do_nms_sort = lib.do_nms_sort
do_nms_sort.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
free_image = lib.free_image
free_image.argtypes = [IMAGE]
letterbox_image = lib.letterbox_image
letterbox_image.argtypes = [IMAGE, c_int, c_int]
letterbox_image.restype = IMAGE
load_meta = lib.get_metadata
lib.get_metadata.argtypes = [c_char_p]
lib.get_metadata.restype = METADATA
load_image = lib.load_image_color
load_image.argtypes = [c_char_p, c_int, c_int]
load_image.restype = IMAGE
rgbgr_image = lib.rgbgr_image
rgbgr_image.argtypes = [IMAGE]
predict_image = lib.network_predict_image
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
res.append((meta.names[i], out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
def video_detect(net, meta, frame, frame_tmp, thresh=.5, hier_thresh=.5, nms=.45):
img_arr = Image.fromarray(frame) # 将frame保存到本地frame_tmp
img_goal = img_arr.save(frame_tmp)
im = load_image(frame_tmp, 0, 0) # 从本地读取图像
num = c_int(0)
pnum = pointer(num)
predict_image(net, im)
dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms): do_nms_obj(dets, num, meta.classes, nms);
res = []
for j in range(num):
for i in range(meta.classes):
if dets[j].prob[i] > 0:
b = dets[j].bbox
ltx = int(b.x - b.w / 2)
lty = int(b.y - b.h / 2)
rbx = int(b.x + b.w / 2)
rby = int(b.y + b.h / 2)
cv2.rectangle(frame, (ltx, lty), (rbx, rby), (0, 255, 0), 2)
res.append([ltx, lty, rbx, rby, dets[j].prob[i]]) # 左上角 右下角 置信度
free_image(im)
free_detections(dets, num)
return res
if __name__ == "__main__":
net = load_net("/home/gjw/darknet-pjreddie/kitti/TestFile/yolov3_kitti.cfg",
"/home/gjw/darknet-pjreddie/kitti/TestFile/yolov3_kitti_final.weights", 0)
meta = load_meta("/home/gjw/darknet-pjreddie/kitti/TestFile/kitti.data")
video_dir = '/home/gjw/darknet-pjreddie/kitti1.avi'
frame_tmp = "/home/gjw/darknet-pjreddie/kitti/video_tmp.jpg" # 暂时保存图像
cap = cv2.VideoCapture(video_dir)
count = 0
while (1):
begin = time.time() # 开始计时
r, frame = cap.read()
if r is False:
print("load video or capture error !")
break
res = video_detect(net, meta, frame, frame_tmp) # frame获取的当前帧，frame_tmp临时存放图像的绝对路径
cv2.imshow("result", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
end = time.time()
fps = 1 / (end - begin)
print(fps)
cap.release()