一、功能与环境说明
程序功能简介: 使用yolo训练,OpenCV调用、实现打哈欠、手机、抽烟、系安全带,口罩检测。
运行测试过的系统环境: 分别为 windows系统、Linux系统、嵌入式Linux系统32位、嵌入式Linux系统64位。
运行测试过的硬件环境: 分别为 普通笔记本电脑(i3、i5、i7)、RK3399、树莓派4B
yolo环境搭建方法:https://pjreddie.com/darknet/yolo/
darknet框架安装教程:https://pjreddie.com/darknet/install/
二、OpenCV调用代码
2.1 .h头文件代码
#ifndef SDK_THREAD_H #define SDK_THREAD_H #include <QThread> #include <QImage> #include "opencv2/core/core.hpp" #include "opencv2/core/core_c.h" #include "opencv2/objdetect.hpp" #include "opencv2/highgui.hpp" #include "opencv2/imgproc.hpp" #include <fstream> #include <sstream> #include <iostream> #include <opencv2/dnn.hpp> #include <opencv2/imgproc.hpp> #include <vector> #include <QDebug> using namespace cv; using namespace std; using namespace dnn; //视频音频编码线程 class SDK_Thread: public QThread { Q_OBJECT public: void postprocess(Mat& frame, const vector<Mat>& outs, float confThreshold, float nmsThreshold); void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame); vector<String> getOutputsNames(Net&net); QImage Mat2QImage(const Mat& mat); Mat QImage2cvMat(QImage image); protected: void run(); signals: void LogSend(QString text); void VideoDataOutput(QImage); //输出信号 }; extern QImage save_image; extern bool sdk_run_flag; extern string names_file; extern String model_def; extern String weights; #endif // SDK_THREAD_H
2.2 .cpp文件代码
#include "sdk_thread.h" QImage save_image; //用于行为分析的图片 bool sdk_run_flag=1; Mat SDK_Thread::QImage2cvMat(QImage image) { Mat mat; switch(image.format()) { case QImage::Format_ARGB32: case QImage::Format_RGB32: case QImage::Format_ARGB32_Premultiplied: mat = Mat(image.height(), image.width(), CV_8UC4, (void*)image.constBits(), image.bytesPerLine()); break; case QImage::Format_RGB888: mat = Mat(image.height(), image.width(), CV_8UC3, (void*)image.constBits(), image.bytesPerLine()); cvtColor(mat, mat, CV_BGR2RGB); break; case QImage::Format_Indexed8: mat = Mat(image.height(), image.width(), CV_8UC1, (void*)image.constBits(), image.bytesPerLine()); break; } return mat; } QImage SDK_Thread::Mat2QImage(const Mat& mat) { // 8-bits unsigned, NO. OF CHANNELS = 1 if(mat.type() == CV_8UC1) { QImage image(mat.cols, mat.rows, QImage::Format_Indexed8); // Set the color table (used to translate colour indexes to qRgb values) image.setColorCount(256); for(int i = 0; i < 256; i++) { image.setColor(i, qRgb(i, i, i)); } // Copy input Mat uchar *pSrc = mat.data; for(int row = 0; row < mat.rows; row ++) { uchar *pDest = image.scanLine(row); memcpy(pDest, pSrc, mat.cols); pSrc += mat.step; } return image; } // 8-bits unsigned, NO. OF CHANNELS = 3 else if(mat.type() == CV_8UC3) { // Copy input Mat const uchar *pSrc = (const uchar*)mat.data; // Create QImage with same dimensions as input Mat QImage image(pSrc, mat.cols, mat.rows, mat.step, QImage::Format_RGB888); return image.rgbSwapped(); } else if(mat.type() == CV_8UC4) { // Copy input Mat const uchar *pSrc = (const uchar*)mat.data; // Create QImage with same dimensions as input Mat QImage image(pSrc, mat.cols, mat.rows, mat.step, QImage::Format_ARGB32); return image.copy(); } else { return QImage(); } } vector<string> classes; vector<String> SDK_Thread::getOutputsNames(Net&net) { static vector<String> names; if (names.empty()) { //Get the indices of the output layers, i.e. the layers with unconnected outputs vector<int> outLayers = net.getUnconnectedOutLayers(); //get the names of all the layers in the network vector<String> layersNames = net.getLayerNames(); // Get the names of the output layers in names names.resize(outLayers.size()); for (size_t i = 0; i < outLayers.size(); ++i) names[i] = layersNames[outLayers[i] - 1]; } return names; } void SDK_Thread::drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame) { //Draw a rectangle displaying the bounding box rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3); //Get the label for the class name and its confidence string label = format("%.5f", conf); if (!classes.empty()) { CV_Assert(classId < (int)classes.size()); label = classes[classId] + ":" + label; } LogSend(tr("识别到的标签:%1").arg(QString::fromStdString(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 - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED); putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0, 0, 0), 1); } void SDK_Thread::postprocess(Mat& frame, const vector<Mat>& outs, float confThreshold, float nmsThreshold) { vector<int> classIds; vector<float> confidences; vector<Rect> boxes; for (size_t i = 0; i < outs.size(); ++i) { // Scan through all the bounding boxes output from the network and keep only the // ones with high confidence scores. Assign the box's class label as the class // with the highest score for the box. float* data = (float*)outs[i].data; for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols) { Mat scores = outs[i].row(j).colRange(5, outs[i].cols); Point classIdPoint; double confidence; // Get the value and location of the maximum score minMaxLoc(scores, 0, &confidence, 0, &classIdPoint); if (confidence > confThreshold) { int centerX = (int)(data[0] * frame.cols); int centerY = (int)(data[1] * frame.rows); int width = (int)(data[2] * frame.cols); int height = (int)(data[3] * frame.rows); int left = centerX - width / 2; int top = centerY - height / 2; classIds.push_back(classIdPoint.x); confidences.push_back((float)confidence); boxes.push_back(Rect(left, top, width, height)); } } } // Perform non maximum suppression to eliminate redundant overlapping boxes with // lower confidences vector<int> indices; NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices); for (size_t i = 0; i < indices.size(); ++i) { int idx = indices[i]; Rect box = boxes[idx]; drawPred(classIds[idx], confidences[idx], box.x, box.y, box.x + box.width, box.y + box.height, frame); } } string names_file; String model_def; String weights; void SDK_Thread::run() { Mat frame,frame_src,blob; int inpWidth, inpHeight; //String names_file = "D:/linux-share-dir/yolo_v3/car/yolo.names"; //String model_def = "D:/linux-share-dir/yolo_v3/car/yolov3.cfg"; //String weights = "D:/linux-share-dir/yolo_v3/car/yolov3.weights"; double thresh = 0.5; double nms_thresh = 0.4; //0.4 0.25 inpWidth = inpHeight = 320; //416 608 //read names ifstream ifs(names_file.c_str()); string line; while(getline(ifs, line))classes.push_back(line); //初始化模型 Net net = readNetFromDarknet(model_def, weights); net.setPreferableBackend(DNN_BACKEND_OPENCV); net.setPreferableTarget(DNN_TARGET_CPU); QImage use_image; LogSend("开始进行行为分析.\n"); //VideoCapture capture(0);// VideoCapture:OENCV中新增的类,捕获视频并显示出来 while(sdk_run_flag) { if(save_image.isNull())continue; LogSend(tr("开始识别------>\n")); //capture >> frame; //得到源图片 //use_image.load("D:/linux-share-dir/car_1.jpg"); frame_src=QImage2cvMat(save_image); cvtColor(frame_src, frame, CV_RGB2BGR); //frame=imread("D:/linux-share-dir/car_1.jpg");// //frame=imread("D:/linux-share-dir/5.jpg"); //in_w=save_image.width(); //in_h=save_image.height(); blobFromImage(frame, blob, 1/255.0, cvSize(inpWidth, inpHeight), Scalar(0,0,0), true, false); vector<Mat> mat_blob; imagesFromBlob(blob, mat_blob); //Sets the input to the network net.setInput(blob); // 运行前向传递以获取输出层的输出 vector<Mat> outs; net.forward(outs, getOutputsNames(net)); postprocess(frame, outs, thresh, nms_thresh); vector<double> layersTimes; double freq = getTickFrequency() / 1000; double t = net.getPerfProfile(layersTimes) / freq; // string label = format("time : %.2f ms", t); //putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255)); LogSend(tr("识别结束---消耗的时间:%1 秒\n").arg(t/1000)); //得到处理后的图像 use_image=Mat2QImage(frame); use_image=use_image.rgbSwapped(); VideoDataOutput(use_image.copy()); } }
三、开发测试效果图
四、车载角度测试效果图