-
Notifications
You must be signed in to change notification settings - Fork 20
/
main.cpp
177 lines (160 loc) · 5.55 KB
/
main.cpp
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
#include <fstream>
#include <sstream>
#include <iostream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace dnn;
using namespace std;
struct Net_config
{
float confThreshold; // Confidence threshold
float nmsThreshold; // Non-maximum suppression threshold
string modelpath;
};
class YOLOV6
{
public:
YOLOV6(Net_config config);
void detect(Mat& frame);
private:
const int inpWidth = 640;
const int inpHeight = 640;
vector<string> class_names;
int num_class;
float confThreshold;
float nmsThreshold;
const bool keep_ratio = true;
Net net;
void drawPred(float conf, int left, int top, int right, int bottom, Mat& frame, int classid);
Mat resize_image(Mat srcimg, int *newh, int *neww, int *top, int *left);
};
YOLOV6::YOLOV6(Net_config config)
{
this->confThreshold = config.confThreshold;
this->nmsThreshold = config.nmsThreshold;
this->net = readNet(config.modelpath);
ifstream ifs("coco.names");
string line;
while (getline(ifs, line)) this->class_names.push_back(line);
this->num_class = class_names.size();
}
Mat YOLOV6::resize_image(Mat srcimg, int *newh, int *neww, int *top, int *left)
{
int srch = srcimg.rows, srcw = srcimg.cols;
*newh = this->inpHeight;
*neww = this->inpWidth;
Mat dstimg;
if (this->keep_ratio && srch != srcw) {
float hw_scale = (float)srch / srcw;
if (hw_scale > 1) {
*newh = this->inpHeight;
*neww = int(this->inpWidth / hw_scale);
resize(srcimg, dstimg, Size(*neww, *newh), INTER_AREA);
*left = int((this->inpWidth - *neww) * 0.5);
copyMakeBorder(dstimg, dstimg, 0, 0, *left, this->inpWidth - *neww - *left, BORDER_CONSTANT, 114);
}
else {
*newh = (int)this->inpHeight * hw_scale;
*neww = this->inpWidth;
resize(srcimg, dstimg, Size(*neww, *newh), INTER_AREA);
*top = (int)(this->inpHeight - *newh) * 0.5;
copyMakeBorder(dstimg, dstimg, *top, this->inpHeight - *newh - *top, 0, 0, BORDER_CONSTANT, 114);
}
}
else {
resize(srcimg, dstimg, Size(*neww, *newh), INTER_AREA);
}
return dstimg;
}
void YOLOV6::drawPred(float conf, int left, int top, int right, int bottom, Mat& frame, int classid) // Draw the predicted bounding box
{
//Draw a rectangle displaying the bounding box
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 0, 255), 2);
//Get the label for the class name and its confidence
string label = format("%.2f", conf);
label = this->class_names[classid] + ":" + label;
//Display the label at the top of the bounding box
int baseLine;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
top = max(top, labelSize.height);
//rectangle(frame, Point(left, top - int(1.5 * labelSize.height)), Point(left + int(1.5 * labelSize.width), top + baseLine), Scalar(0, 255, 0), FILLED);
putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 255, 0), 1);
}
void YOLOV6::detect(Mat& frame)
{
int newh = 0, neww = 0, padh = 0, padw = 0;
Mat dstimg = this->resize_image(frame, &newh, &neww, &padh, &padw);
Mat blob = blobFromImage(dstimg, 1 / 255.0, Size(this->inpWidth, this->inpHeight), Scalar(0, 0, 0), true, false);
this->net.setInput(blob);
vector<Mat> outs;
this->net.forward(outs, this->net.getUnconnectedOutLayersNames());
int num_proposal = outs[0].size[0];
int nout = outs[0].size[1];
if (outs[0].dims > 2)
{
num_proposal = outs[0].size[1];
nout = outs[0].size[2];
outs[0] = outs[0].reshape(0, num_proposal);
}
/////generate proposals
vector<float> confidences;
vector<Rect> boxes;
vector<int> classIds;
float ratioh = (float)frame.rows / newh, ratiow = (float)frame.cols / neww;
int n = 0, row_ind = 0; ///cx,cy,w,h,box_score,class_score
float* pdata = (float*)outs[0].data;
for (n = 0; n < num_proposal; n++) ///ÌØÕ÷ͼ³ß¶È
{
float box_score = pdata[4];
if (box_score > this->confThreshold)
{
Mat scores = outs[0].row(row_ind).colRange(5, nout);
Point classIdPoint;
double max_class_socre;
// Get the value and location of the maximum score
minMaxLoc(scores, 0, &max_class_socre, 0, &classIdPoint);
max_class_socre *= box_score;
if (max_class_socre > this->confThreshold)
{
const int class_idx = classIdPoint.x;
float cx = (pdata[0] - padw) * ratiow; ///cx
float cy = (pdata[1] - padh) * ratioh; ///cy
float w = pdata[2] * ratiow; ///w
float h = pdata[3] * ratioh; ///h
int left = int(cx - 0.5 * w);
int top = int(cy - 0.5 * h);
confidences.push_back((float)max_class_socre);
boxes.push_back(Rect(left, top, (int)(w), (int)(h)));
classIds.push_back(class_idx);
}
}
row_ind++;
pdata += nout;
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with
// lower confidences
vector<int> indices;
dnn::NMSBoxes(boxes, confidences, this->confThreshold, this->nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
Rect box = boxes[idx];
this->drawPred(confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame, classIds[idx]);
}
}
int main()
{
Net_config YOLOV6_nets = { 0.3, 0.5, "onnxmodel/yolov6s.onnx" };
YOLOV6 YOLOV6_model(YOLOV6_nets);
string imgpath = "images/image1.jpg";
Mat srcimg = imread(imgpath);
YOLOV6_model.detect(srcimg);
static const string kWinName = "Deep learning object detection in OpenCV";
namedWindow(kWinName, WINDOW_NORMAL);
imshow(kWinName, srcimg);
waitKey(0);
destroyAllWindows();
}