-
Notifications
You must be signed in to change notification settings - Fork 1
/
yolo_webcam.py
181 lines (88 loc) · 3.23 KB
/
yolo_webcam.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
#Written by Junhyeok Jeong
#!/usr/bin/env python
# coding: utf-8
# In[8]:
import cv2
# In[9]:
import numpy as np
import time
# In[10]:
#Load YOLO
net = cv2.dnn.readNet("/home/kimchi/graspinglab/darknet/yolov3.weights","/home/kimchi/graspinglab/darknet/cfg/yolov3.cfg") # Original yolov3
#net = cv2.dnn.readNet("yolov3-tiny.weights","yolov3-tiny.cfg") #Tiny Yolo
classes = []
with open("/home/kimchi/graspinglab/darknet/data/coco.names","r") as f:
classes = [line.strip() for line in f.readlines()]
# In[11]:
print(classes)
# In[12]:
layer_names = net.getLayerNames()
outputlayers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# In[ ]:
# In[13]:
colors= np.random.uniform(0,255,size=(len(classes),3))
# In[ ]:
# In[14]:
#loading image
cap=cv2.VideoCapture(0) #0 for 1st webcam
font = cv2.FONT_HERSHEY_PLAIN
starting_time= time.time()
frame_id = 0
while True:
_,frame= cap.read() #
frame_id+=1
height,width,channels = frame.shape
#detecting objects
#frame = cv2.resize(frame, (640, 640))
blob = cv2.dnn.blobFromImage(frame,0.00392,(320,320),(0,0,0),True,crop=False)
net.setInput(blob)
outs = net.forward(outputlayers)
#print(outs[1])
#Showing info on screen/ get confidence score of algorithm in detecting an object in blob
class_ids=[]
confidences=[]
boxes=[]
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.3:
#onject detected
center_x= int(detection[0]*width)
center_y= int(detection[1]*height)
w = int(detection[2]*width)
h = int(detection[3]*height)
#cv2.circle(img,(center_x,center_y),10,(0,255,0),2)
#rectangle co-ordinaters
x=int(center_x - w/2)
y=int(center_y - h/2)
#cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
boxes.append([x,y,w,h]) #put all rectangle areas
confidences.append(float(confidence)) #how confidence was that object detected and show that percentage
class_ids.append(class_id) #name of the object tha was detected
indexes = cv2.dnn.NMSBoxes(boxes,confidences,0.4,0.6)
for i in range(len(boxes)):
if i in indexes:
x,y,w,h = boxes[i]
label = str(classes[class_ids[i]])
confidence= confidences[i]
color = colors[class_ids[i]]
cv2.rectangle(frame,(x,y),(x+w,y+h),color,2)
cv2.putText(frame,label+" "+str(round(confidence,2)),(x,y+30),font,1,(255,255,255),2)
elapsed_time = time.time() - starting_time
fps=frame_id/elapsed_time
cv2.putText(frame,"FPS:"+str(round(fps,2)),(10,50),font,2,(0,0,0),1)
cv2.imshow("Image",frame)
key = cv2.waitKey(1) #wait 1ms the loop will start again and we will process the next frame
if key == 27: #esc key stops the process
break
cap.release()
cv2.destroyAllWindows()
# In[ ]:
# In[ ]:
# In[ ]:
# In[ ]:
# In[ ]:
# In[9]:
# In[ ]: