python-examples-cv/gradient_orientation.py at master · Irenaeusw/python-examples-cv · 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
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
#####################################################################

# Example : perform generic live display of gradient orientations
# (which form the essensce of the Histogram of Oriented Gradient (HOG) feature)
# from a video file specified on the command line
# (e.g. python FILE.py video_file) or from an attached web camera

# Author : Toby Breckon, [email protected]

# https://www.learnopencv.com/histogram-of-oriented-gradients/

# Copyright (c) 2018 Dept. Computer Science,
#                    Durham University, UK
# License : LGPL - http://www.gnu.org/licenses/lgpl.html

#####################################################################

import cv2
import argparse
import sys
import math
import numpy as np

#####################################################################

keep_processing = True;

# parse command line arguments for camera ID or video file

parser = argparse.ArgumentParser(description='Perform ' + sys.argv[0] + ' example operation on incoming camera/video image')
parser.add_argument("-c", "--camera_to_use", type=int, help="specify camera to use", default=0)
parser.add_argument('video_file', metavar='video_file', type=str, nargs='?', help='specify optional video file')
args = parser.parse_args()

#####################################################################

# define video capture object

cap = cv2.VideoCapture();

# define display window names

windowNameGx = "Gradient - Gx"; # window name
windowNameGy = "Gradient - Gy"; # window name
windowNameAngle = "Gradient Angle"; # window name

# if command line arguments are provided try to read video_name
# otherwise default to capture from attached camera

if (((args.video_file) and (cap.open(str(args.video_file))))
    or (cap.open(args.camera_to_use))):

    # create window by name (as resizable)

    cv2.namedWindow(windowNameGx, cv2.WINDOW_NORMAL);
    cv2.namedWindow(windowNameGy, cv2.WINDOW_NORMAL);
    cv2.namedWindow(windowNameAngle, cv2.WINDOW_NORMAL);

    while (keep_processing):

        # start a timer (to see how long processing and display takes)

        start_t = cv2.getTickCount();

        # if video file successfully open then read frame from video

        if (cap.isOpened):
            ret, frame = cap.read();

            # when we reach the end of the video (file) exit cleanly

            if (ret == 0):
                keep_processing = False;
                continue;

        # compute the gradients in the x and y directions separately
        # N.B from here onward these images are 32-bit float

        gx = cv2.Sobel(frame, cv2.CV_32F, 1, 0);
        gy = cv2.Sobel(frame, cv2.CV_32F, 0, 1);

        # calculate gradient magnitude and direction (in degrees)

        mag, angle = cv2.cartToPolar(gx, gy, angleInDegrees=True);

        # normalize

        gx = np.abs(gx);
        gy = np.abs(gy);
        angle = np.abs(angle);

        # normalize other values 0 -> 180

        gx = cv2.normalize(gx, None, 0, 255, cv2.NORM_MINMAX);
        gy = cv2.normalize(gy, None, 0, 255, cv2.NORM_MINMAX);
        angle = cv2.normalize(angle, None, 0, 180, cv2.NORM_MINMAX);

        # for the angle take the max across all three channels

        (aB, aG, aR) = cv2.split(angle);
        angle = np.maximum(np.maximum(aR, aG), aB);

        # display images (as 8-bit)

        cv2.imshow(windowNameGx,gx.astype(np.uint8));
        cv2.imshow(windowNameGy,gy.astype(np.uint8));
        cv2.imshow(windowNameAngle,angle.astype(np.uint8));

        # stop the timer and convert to ms. (to see how long processing and display takes)

        stop_t = ((cv2.getTickCount() - start_t)/cv2.getTickFrequency()) * 1000;

        # start the event loop - essential

        # cv2.waitKey() is a keyboard binding function (argument is the time in milliseconds).
        # It waits for specified milliseconds for any keyboard event.
        # If you press any key in that time, the program continues.
        # If 0 is passed, it waits indefinitely for a key stroke.
        # (bitwise and with 0xFF to extract least significant byte of multi-byte response)
        # here we use a wait time in ms. that takes account of processing time already used in the loop

        # wait 40ms or less depending on processing time taken (i.e. 1000ms / 25 fps = 40 ms)

        key = cv2.waitKey(max(2, 40 - int(math.ceil(stop_t)))) & 0xFF;

        # It can also be set to detect specific key strokes by recording which key is pressed

        # e.g. if user presses "x" then exit  / press "f" for fullscreen display

        if (key == ord('x')):
            keep_processing = False;
        elif (key == ord('f')):
            cv2.setWindowProperty(windowNameAngle, cv2.WND_PROP_FULLSCREEN, cv2.WINDOW_FULLSCREEN);

    # close all windows

    cv2.destroyAllWindows()

else:
    print("No video file specified or camera connected.");

#####################################################################