opencv 识别机车

效果1 识别摩托

效果 公路场景撞击现场

定义识别名称

const char* classNames[] = { “背景”,
“飞机”, “自行车”, “鸟”, “船”,
“瓶子”, “大汽车”, “小汽车”, “猫”, “椅子”,
“奶牛”, “餐桌”, “狗”, “马”,
“机车”, “人”, “花盆植物”,
“羊”, “沙发”, “火车”, “tv监视器” };

    String file_path = parser.getPathToApplication() + "/"; 
	String modelConfiguration = file_path + "xx.prototxt";
	String modelBinary = file_path + "model.caffemodel";
	try
	{
      //加载深度神经网络模型
		dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
		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/chuanqi305/MobileNet-SSD" << endl;
			exit(-1);
		}
		net.setPreferableTarget(DNN_TARGET_OPENCL);

//定义图片，也可以从rtsp摄像头读取后 解码放到mat中，具体看我文章
rtsp读取摄像头进行算法识别

string image_file_name = "J:/bbbbb.jpg";
cv::Mat frame = cv::imread(image_file_name, CV_LOAD_IMAGE_COLOR);

判别过程

			Mat inputBlob = blobFromImage(frame, inScaleFactor,
				Size(inWidth, inHeight),
				Scalar(meanVal, meanVal, meanVal),
				false, false); //Convert Mat to batch of images


			net.setInput(inputBlob); //set the network input
			Mat detection = net.forward(); //compute output

			vector<double> layersTimings;
			double freq = getTickFrequency() / 1000;
			double time = net.getPerfProfile(layersTimings) / freq;

			Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
			float confidenceThreshold = 0.5;// 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 left = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
					int top = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
					int right = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
					int bottom = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);

					rectangle(frame, Point(left, top), Point(right, bottom), Scalar(0, 255, 0),2);
					String label = format("%s: %.2f", classNames[objectClass], confidence);
					int baseLine = 0;
					Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
					top = max(top, labelSize.height);
					rectangle(frame, Point(left, top - labelSize.height),
						Point(left + labelSize.width, top + baseLine+2),
						Scalar(0, 0, 255),FILLED);
					
					putTextZH(frame, label.c_str(), Point(left, top), Scalar(255, 255, 255), 18);
					/*putText(frame, label, Point(left, top),
						FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 0));*/
				}
			}

以上使用opencv3.4.1 win7 win10 调试通过，在linux下面都是一样的过程，整个的

训练过程描述

可以使用多种方式，一种是yolo，一种是tensorflow模式训练模型，比较难的是逻辑模型，也就是行为识别，没有好的显卡很难做，这里没有写真正的详细过程，后续文章会写两种模式来训练模型。请关注我.