-
Notifications
You must be signed in to change notification settings - Fork 0
/
image_detection_yolo.py
191 lines (164 loc) · 5.76 KB
/
image_detection_yolo.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
import argparse
import time
import cv2
import numpy as np
parser = argparse.ArgumentParser()
parser.add_argument('--webcam', help="Y/N", default="Y")
parser.add_argument('--play_video', help="Y/N", default="N")
parser.add_argument('--image', help="Y/N", default="N")
parser.add_argument('--video_path', help="Path of video file", default="")
parser.add_argument(
'--image_path', help="Path of image to detect objects", default="")
parser.add_argument('--verbose', help="To print statements", default=True)
args = parser.parse_args()
#Load yolo
def load_yolo():
net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
classes = []
with open("coco.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layers_names = net.getLayerNames()
output_layers = [
layers_names[i[0] - 1] for i in net.getUnconnectedOutLayers()
]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
return net, classes, colors, output_layers
def load_image(img_path):
# image loading
img = cv2.imread(img_path)
img = cv2.resize(img, None, fx=0.4, fy=0.4)
height, width, channels = img.shape
return img, height, width, channels
def start_webcam():
cap = cv2.VideoCapture(0)
print("cap is : ",cap)
return cap
def display_blob(blob):
'''
Three images each for RED, GREEN, BLUE channel
'''
for b in blob:
for n, imgb in enumerate(b):
cv2.imshow(str(n), imgb)
def detect_objects(img, net, outputLayers):
blob = cv2.dnn.blobFromImage(
img,
scalefactor=0.00392,
size=(320, 320),
mean=(0, 0, 0),
swapRB=True,
crop=False)
net.setInput(blob)
outputs = net.forward(outputLayers)
return blob, outputs
def get_box_dimensions(outputs, height, width):
boxes = []
confs = []
class_ids = []
for output in outputs:
for detect in output:
scores = detect[5:]
class_id = np.argmax(scores)
conf = scores[class_id]
if conf > 0.3:
center_x = int(detect[0] * width)
center_y = int(detect[1] * height)
w = int(detect[2] * width)
h = int(detect[3] * height)
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confs.append(float(conf))
class_ids.append(class_id)
return boxes, confs, class_ids
def draw_labels(boxes, confs, colors, class_ids, classes, img):
indexes = cv2.dnn.NMSBoxes(boxes, confs, 0.5, 0.4)
font = cv2.FONT_HERSHEY_PLAIN
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
color = colors[i]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(img, label, (x, y - 5), font, 1, color, 1)
cv2.imshow("Image", img)
def image_detect(img_path):
model, classes, colors, output_layers = load_yolo()
image, height, width, channels = load_image(img_path)
blob, outputs = detect_objects(image, model, output_layers)
boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
draw_labels(boxes, confs, colors, class_ids, classes, image)
while True:
key = cv2.waitKey(1)
if key == 27:
break
def print_labels(classes, class_ids):
s = []
for val in class_ids:
s.append(classes[class_ids])
print("***classes found: ", ",".join(s))
def webcam_detect():
model, classes, colors, output_layers = load_yolo()
print("before load")
cap = start_webcam()
print("after load")
while True:
#read frame
_, frame = cap.read()
height, width, channels = frame.shape
t = int(time.time())
if t%10 == 0:
cv2.imwrite('current.png', frame)
#detect object
blob, outputs = detect_objects(frame, model, output_layers)
#print("** outputs: ",outputs)
boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
#if len(confs) > 0:
#print("*** confs:{} {} ".format(max(confs), classes[class_ids[confs.index(max(confs))]]))
#print("***8 class_ids: ",class_ids)
#print_labels(classes,class_ids)
draw_labels(boxes, confs, colors, class_ids, classes, frame)
#esc key is exit key
key = cv2.waitKey(1)
if key == 27:
break
cap.release()
def start_video(video_path):
print(" video before load")
model, classes, colors, output_layers = load_yolo()
cap = cv2.VideoCapture(video_path)
print("after load")
while True:
_, frame = cap.read()
t = int(time.time())
if t%10 == 0:
cv2.imwrite('current.png', frame)
height, width, channels = frame.shape
blob, outputs = detect_objects(frame, model, output_layers)
boxes, confs, class_ids = get_box_dimensions(outputs, height, width)
draw_labels(boxes, confs, colors, class_ids, classes, frame)
key = cv2.waitKey(1)
#esc key is exit key
if key == 27:
break
cap.release()
if __name__ == '__main__':
webcam = args.webcam
video_play = args.play_video
image = args.image
print("Args: ",args)
if webcam == "Y":
if args.verbose:
print('---- Starting Web Cam object detection ----')
webcam_detect()
if video_play == "Y":
video_path = args.video_path
if args.verbose:
print('Opening ' + video_path + " .... ")
start_video(video_path)
if image == "Y":
image_path = args.image_path
if args.verbose:
print("Opening " + image_path + " .... ")
image_detect(image_path)
cv2.destroyAllWindows()