openCV-with-python/real_time_object_detection.py at master · Utkarsh2604/openCV-with-python · GitHub

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
'''
This python file detects objects in real-time
To run this file clone the CAFFE model used in this file from https://github.com/y-pankaj/Caffe-files-for-object-detection
The repo contains two files. One of them is the pretrained CAFFE model which contains the weights and the other files is to deploy this model in out python file
Put both the files in the same directory as this python file and then run this python file ( python real_time_object_detection.py for ubuntu)
This file makes use of dnn module of OpenCV for object detection.
The below code has comments along with it to make this file understandable.
'''

# importing the packages for the project
from imutils.video import VideoStream
from imutils.video import FPS
import numpy as np
import argparse
import imutils
import time
import cv2


# these classes can be detected by this model
CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
	"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
	"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
	"sofa", "train", "tvmonitor"]

# array of different colors
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

# load our serialized model from disk
print("[INFO] loading model...")
net = cv2.dnn.readNetFromCaffe('MobileNetSSD_deploy.prototxt.txt', 'MobileNetSSD_deploy.caffemodel')

# initializing the video stream
# and initializng the FPS counter
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
time.sleep(2.0)
fps = FPS().start()

# loop over the frames from the video stream
while True:
	# each frame is resized to a width of 600 pixels
	frame = vs.read()
	frame = imutils.resize(frame, width=600)

	# grab the frame dimensions and convert it to a blob
    # blobFromImage does mean substraction and scaling
	(h, w) = frame.shape[:2]
	blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),
		0.007843, (300, 300), 127.5)

	# pass the blob through the network and obtain the detections and
	# predictions
	net.setInput(blob)
	detections = net.forward()

	for i in np.arange(0, detections.shape[2]):
		# extract the confidence (i.e., probability) associated with
		# the prediction
		confidence = detections[0, 0, i, 2]

		# filter out weak detections by ensuring the `confidence` is
		# greater than the minimum confidence
		if confidence > .2:
			# extract the index of the class label from the
			# `detections`, then compute the (x, y)-coordinates of
			# the bounding box for the object
			idx = int(detections[0, 0, i, 1])
			box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
			(startX, startY, endX, endY) = box.astype("int")


			width_in_pixels = endX - startX

			# draw the prediction on the frame
			label = "{}: {:.2f} %".format(CLASSES[idx],
				confidence * 100)
			cv2.rectangle(frame, (startX, startY), (endX, endY),
				COLORS[idx], 2)
			y = startY - 15 if startY - 15 > 15 else startY + 15
			cv2.putText(frame, label, (startX, y),
				cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)


	# show the output frame
	cv2.imshow("Frame", frame)
	key = cv2.waitKey(1) & 0xFF

	# if the `q` key was pressed, break from the loop
	if key == ord("q"):
		break

	# update the FPS counter
	fps.update()

# stop the timer and display FPS information
fps.stop()
print("[INFO] elapsed time: {:.2f}".format(fps.elapsed()))
print("[INFO] approx. FPS: {:.2f}".format(fps.fps()))

cv2.destroyAllWindows()
vs.stop()