本文参考:https://blog.csdn.net/hunzhangzui9837/article/details/82837873
#include
#include
#include
using namespace cv;
using namespace cv::dnn;
using namespace std;
const size_t width = 300;
const size_t height = 300;
const float meanVal = 127.5;
const float scaleFactor = 0.007843f;
const char* classNames[] = { "background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor" };
String modelFile = "C:/Users/18301/Desktop/models_VGGNet_VOC0712Plus_SSD_300x300/models/VGGNet/VOC0712Plus/SSD_300x300/VGG_VOC0712Plus_SSD_300x300_iter_240000.caffemodel";
String model_text_file = "C:/Users/18301/Desktop/models_VGGNet_VOC0712Plus_SSD_300x300/models/VGGNet/VOC0712Plus/SSD_300x300/deploy.prototxt";
int main()
{
VideoCapture capture;
capture.open(0);
namedWindow("input", CV_WINDOW_AUTOSIZE);
int w = capture.get(CAP_PROP_FRAME_WIDTH);
int h = capture.get(CAP_PROP_FRAME_HEIGHT);
printf("frame width : %d, frame height : %d", w, h);
// set up net
Net net = readNetFromCaffe(model_text_file, modelFile);
Mat frame;
//while (capture.read(frame)) //注意:这里提供了两种模式,调用摄像头的时候把该句取消注释即可
while (1)
{
frame = imread("C:/Users/18301/Desktop/car.jpg");
imshow("input", frame);
//预测
Mat inputblob = blobFromImage(frame, scaleFactor, Size(width, height), meanVal, false);
net.setInput(inputblob, "data");
Mat detection = net.forward("detection_out");
//检测
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr());
float confidence_threshold = 0.3;
for (int i = 0; i < detectionMat.rows; i++) {
float confidence = detectionMat.at(i, 2);
if (confidence > confidence_threshold) {
size_t objIndex = (size_t)(detectionMat.at(i, 1));
float tl_x = detectionMat.at(i, 3) * frame.cols;
float tl_y = detectionMat.at(i, 4) * frame.rows;
float br_x = detectionMat.at(i, 5) * frame.cols;
float br_y = detectionMat.at(i, 6) * frame.rows;
Rect object_box((int)tl_x, (int)tl_y, (int)(br_x - tl_x), (int)(br_y - tl_y));
rectangle(frame, object_box, Scalar(0, 0, 255), 2, 8, 0);
putText(frame, format("%s", classNames[objIndex]), Point(tl_x, tl_y), FONT_HERSHEY_SIMPLEX, 1.0, Scalar(255, 0, 0), 2);
}
}
imshow("ssd-video-demo", frame);
char c = waitKey(5);
if (c == 27)
{ // ESC退出
break;
}
}
capture.release();
waitKey(0);
return 0;
}
不过说实话效果不是太好,因为这个SSD模型是基于VGG16的,可能特征表征能力不是太强吧~视频检测就更差了,就不展示了。
实验中的模型链接:SSD Caffe模型