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
197
198
199
200
201
202
203
204
205
206
207
208
209
210
#include <vector>
#include <iostream>
#include <string>
#include "opencv2/core.hpp"
#include "opencv2/core/utility.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/gpu.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/contrib.hpp"
using namespace std;
using namespace cv;
using cv::gpu::GpuMat;
static Mat loadImage(const string& name)
{
Mat image = imread(name, IMREAD_GRAYSCALE);
if (image.empty())
{
cerr << "Can't load image - " << name << endl;
exit(-1);
}
return image;
}
int main(int argc, const char* argv[])
{
CommandLineParser cmd(argc, argv,
"{ image i | pic1.png | input image }"
"{ template t | templ.png | template image }"
"{ scale s | | estimate scale }"
"{ rotation r | | estimate rotation }"
"{ gpu | | use gpu version }"
"{ minDist | 100 | minimum distance between the centers of the detected objects }"
"{ levels | 360 | R-Table levels }"
"{ votesThreshold | 30 | the accumulator threshold for the template centers at the detection stage. The smaller it is, the more false positions may be detected }"
"{ angleThresh | 10000 | angle votes treshold }"
"{ scaleThresh | 1000 | scale votes treshold }"
"{ posThresh | 100 | position votes threshold }"
"{ dp | 2 | inverse ratio of the accumulator resolution to the image resolution }"
"{ minScale | 0.5 | minimal scale to detect }"
"{ maxScale | 2 | maximal scale to detect }"
"{ scaleStep | 0.05 | scale step }"
"{ minAngle | 0 | minimal rotation angle to detect in degrees }"
"{ maxAngle | 360 | maximal rotation angle to detect in degrees }"
"{ angleStep | 1 | angle step in degrees }"
"{ maxSize | 1000 | maximal size of inner buffers }"
"{ help h ? | | print help message }"
);
cmd.about("This program demonstrates arbitary object finding with the Generalized Hough transform.");
if (cmd.has("help"))
{
cmd.printMessage();
return 0;
}
const string templName = cmd.get<string>("template");
const string imageName = cmd.get<string>("image");
const bool estimateScale = cmd.has("scale");
const bool estimateRotation = cmd.has("rotation");
const bool useGpu = cmd.has("gpu");
const double minDist = cmd.get<double>("minDist");
const int levels = cmd.get<int>("levels");
const int votesThreshold = cmd.get<int>("votesThreshold");
const int angleThresh = cmd.get<int>("angleThresh");
const int scaleThresh = cmd.get<int>("scaleThresh");
const int posThresh = cmd.get<int>("posThresh");
const double dp = cmd.get<double>("dp");
const double minScale = cmd.get<double>("minScale");
const double maxScale = cmd.get<double>("maxScale");
const double scaleStep = cmd.get<double>("scaleStep");
const double minAngle = cmd.get<double>("minAngle");
const double maxAngle = cmd.get<double>("maxAngle");
const double angleStep = cmd.get<double>("angleStep");
const int maxSize = cmd.get<int>("maxSize");
if (!cmd.check())
{
cmd.printErrors();
return -1;
}
Mat templ = loadImage(templName);
Mat image = loadImage(imageName);
int method = cv::GeneralizedHough::GHT_POSITION;
if (estimateScale)
method += cv::GeneralizedHough::GHT_SCALE;
if (estimateRotation)
method += cv::GeneralizedHough::GHT_ROTATION;
vector<Vec4f> position;
cv::TickMeter tm;
if (useGpu)
{
GpuMat d_templ(templ);
GpuMat d_image(image);
GpuMat d_position;
Ptr<gpu::GeneralizedHough> d_hough = gpu::GeneralizedHough::create(method);
d_hough->set("minDist", minDist);
d_hough->set("levels", levels);
d_hough->set("dp", dp);
d_hough->set("maxSize", maxSize);
if (estimateScale && estimateRotation)
{
d_hough->set("angleThresh", angleThresh);
d_hough->set("scaleThresh", scaleThresh);
d_hough->set("posThresh", posThresh);
}
else
{
d_hough->set("votesThreshold", votesThreshold);
}
if (estimateScale)
{
d_hough->set("minScale", minScale);
d_hough->set("maxScale", maxScale);
d_hough->set("scaleStep", scaleStep);
}
if (estimateRotation)
{
d_hough->set("minAngle", minAngle);
d_hough->set("maxAngle", maxAngle);
d_hough->set("angleStep", angleStep);
}
d_hough->setTemplate(d_templ);
tm.start();
d_hough->detect(d_image, d_position);
d_hough->downloadResults(d_position, position);
tm.stop();
}
else
{
Ptr<GeneralizedHough> hough = GeneralizedHough::create(method);
hough->set("minDist", minDist);
hough->set("levels", levels);
hough->set("dp", dp);
if (estimateScale && estimateRotation)
{
hough->set("angleThresh", angleThresh);
hough->set("scaleThresh", scaleThresh);
hough->set("posThresh", posThresh);
hough->set("maxSize", maxSize);
}
else
{
hough->set("votesThreshold", votesThreshold);
}
if (estimateScale)
{
hough->set("minScale", minScale);
hough->set("maxScale", maxScale);
hough->set("scaleStep", scaleStep);
}
if (estimateRotation)
{
hough->set("minAngle", minAngle);
hough->set("maxAngle", maxAngle);
hough->set("angleStep", angleStep);
}
hough->setTemplate(templ);
tm.start();
hough->detect(image, position);
tm.stop();
}
cout << "Found : " << position.size() << " objects" << endl;
cout << "Detection time : " << tm.getTimeMilli() << " ms" << endl;
Mat out;
cv::cvtColor(image, out, COLOR_GRAY2BGR);
for (size_t i = 0; i < position.size(); ++i)
{
Point2f pos(position[i][0], position[i][1]);
float scale = position[i][2];
float angle = position[i][3];
RotatedRect rect;
rect.center = pos;
rect.size = Size2f(templ.cols * scale, templ.rows * scale);
rect.angle = angle;
Point2f pts[4];
rect.points(pts);
line(out, pts[0], pts[1], Scalar(0, 0, 255), 3);
line(out, pts[1], pts[2], Scalar(0, 0, 255), 3);
line(out, pts[2], pts[3], Scalar(0, 0, 255), 3);
line(out, pts[3], pts[0], Scalar(0, 0, 255), 3);
}
imshow("out", out);
waitKey();
return 0;
}