RealTimeObjectDetection/detect2.cpp at master · tejasa97/RealTimeObjectDetection · 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
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/core/utils/trace.hpp>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;

string CLASSES[] = {"background", "aeroplane", "bicycle", "bird", "boat",
	"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
	"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
	"sofa", "train", "tvmonitor"};


int main(int argc, char **argv)
{
    CV_TRACE_FUNCTION();
    String modelTxt = "MobileNetSSD_deploy.prototxt.txt";
    String modelBin = "MobileNetSSD_deploy.caffemodel";

    String imageFile = (argc > 1) ? argv[1] : "re.jpg";
    Net net = dnn::readNetFromCaffe(modelTxt, modelBin);
    if (net.empty())
    {
        std::cerr << "Can't load network by using the following files: " << std::endl;
        std::cerr << "prototxt:   " << modelTxt << std::endl;
        std::cerr << "caffemodel: " << modelBin << std::endl;
        exit(-1);
    }
	VideoCapture cap;
	cap.open(0);
    // Mat img = imread(imageFile);
    clock_t begin_time;
    while(1)
	{
		// if (img.empty())
	 //    {
		// std::cerr << "Can't read image from the file: " << imageFile << std::endl;
		// exit(-1);
	 //    }
	    begin_time = clock();
		// do something
	    Mat img, img2;
	    cap >> img;
	    resize(img, img2, Size(300,300));
	    Mat inputBlob = blobFromImage(img2, 0.007843, Size(300,300), Scalar(127.5, 127.5, 127.5), false);

	    net.setInput(inputBlob, "data");
	    Mat detection = net.forward("detection_out");
	    Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());

	    ostringstream ss;
	    float confidenceThreshold = 0.2;
	    for (int i = 0; i < detectionMat.rows; i++)
	    {
			float confidence = detectionMat.at<float>(i, 2);

			if (confidence > confidenceThreshold)
				{
				    int idx = static_cast<int>(detectionMat.at<float>(i, 1));
				    int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * img.cols);
				    int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * img.rows);
				    int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * img.cols);
				    int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * img.rows);

				    Rect object((int)xLeftBottom, (int)yLeftBottom,
				                (int)(xRightTop - xLeftBottom),
				                (int)(yRightTop - yLeftBottom));

				    rectangle(img, object, Scalar(0, 255, 0), 2);

				    // cout << CLASSES[idx] << ": " << confidence << endl;

				    ss.str("");
				    ss << confidence;
				    String conf(ss.str());
				    String label = CLASSES[idx] + ": " + conf;
				    int baseLine = 0;
				    Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
				    putText(img2, label, Point(xLeftBottom, yLeftBottom),
				            FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,0,0));
				}
	    }
	    imshow("detections", img2);
	    //if (waitKey(1) && 0xFF)
	    	//break;
	    //std::cout << 1 / (float(clock () - begin_time ) /  CLOCKS_PER_SEC)<<endl;
	    // waitKey();
	}
	return 0;
}