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
#include <opencv2/dnn.hpp>
#include <opencv2/dnn/shape_utils.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace std;
using namespace cv::dnn;
const char* classNames[] = {"background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor"};
const char* about = "This sample uses Single-Shot Detector "
"(https://arxiv.org/abs/1512.02325) "
"to detect objects on camera/video/image.\n"
".caffemodel model's file is available here: "
"https://github.com/weiliu89/caffe/tree/ssd#models\n"
"Default network is 300x300 and 20-classes VOC.\n";
const char* params
= "{ help | false | print usage }"
"{ proto | | model configuration }"
"{ model | | model weights }"
"{ camera_device | 0 | camera device number}"
"{ video | | video or image for detection}"
"{ min_confidence | 0.5 | min confidence }";
int main(int argc, char** argv)
{
cv::CommandLineParser parser(argc, argv, params);
if (parser.get<bool>("help"))
{
cout << about << endl;
parser.printMessage();
return 0;
}
String modelConfiguration = parser.get<string>("proto");
String modelBinary = parser.get<string>("model");
//! [Initialize network]
dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
//! [Initialize network]
if (net.empty())
{
cerr << "Can't load network by using the following files: " << endl;
cerr << "prototxt: " << modelConfiguration << endl;
cerr << "caffemodel: " << modelBinary << endl;
cerr << "Models can be downloaded here:" << endl;
cerr << "https://github.com/weiliu89/caffe/tree/ssd#models" << endl;
exit(-1);
}
VideoCapture cap;
if (parser.get<String>("video").empty())
{
int cameraDevice = parser.get<int>("camera_device");
cap = VideoCapture(cameraDevice);
if(!cap.isOpened())
{
cout << "Couldn't find camera: " << cameraDevice << endl;
return -1;
}
}
else
{
cap.open(parser.get<String>("video"));
if(!cap.isOpened())
{
cout << "Couldn't open image or video: " << parser.get<String>("video") << endl;
return -1;
}
}
for (;;)
{
cv::Mat frame;
cap >> frame; // get a new frame from camera/video or read image
if (frame.empty())
{
waitKey();
break;
}
if (frame.channels() == 4)
cvtColor(frame, frame, COLOR_BGRA2BGR);
//! [Prepare blob]
Mat inputBlob = blobFromImage(frame, 1.0f, Size(300, 300), Scalar(104, 117, 123), false, false); //Convert Mat to batch of images
//! [Prepare blob]
//! [Set input blob]
net.setInput(inputBlob, "data"); //set the network input
//! [Set input blob]
//! [Make forward pass]
Mat detection = net.forward("detection_out"); //compute output
//! [Make forward pass]
vector<double> layersTimings;
double freq = getTickFrequency() / 1000;
double time = net.getPerfProfile(layersTimings) / freq;
ostringstream ss;
ss << "FPS: " << 1000/time << " ; time: " << time << " ms";
putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255));
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
float confidenceThreshold = parser.get<float>("min_confidence");
for(int i = 0; i < detectionMat.rows; i++)
{
float confidence = detectionMat.at<float>(i, 2);
if(confidence > confidenceThreshold)
{
size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);
ss.str("");
ss << confidence;
String conf(ss.str());
Rect object(xLeftBottom, yLeftBottom,
xRightTop - xLeftBottom,
yRightTop - yLeftBottom);
rectangle(frame, object, Scalar(0, 255, 0));
String label = String(classNames[objectClass]) + ": " + conf;
int baseLine = 0;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height),
Size(labelSize.width, labelSize.height + baseLine)),
Scalar(255, 255, 255), FILLED);
putText(frame, label, Point(xLeftBottom, yLeftBottom),
FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,0,0));
}
}
imshow("detections", frame);
if (waitKey(1) >= 0) break;
}
return 0;
} // main