【基于opencv3.4.1的Mobilenet_SSD深度学习模型的调用与目标识别】

   目前，常见的目标检测算法，如Faster R-CNN，存在着速度慢的缺点。该论文提出的SSD方法，不仅提高了速度，而且提高了准确度。SSD:

该论文的核心思想：

本文中我们主要总结前人工作，通过opencv调用ssd生成模型，实现对图像或视频流中目标的识别。

其中mobile_net的模型文件与描述文件位于opencv安装路径的C:\opencv\opencv\sources\samples\data\dnn\...中。

主要代码如下：

#include<opencv2/opencv.hpp>

#include <opencv2/dnn.hpp>

#include <iostream>



using namespace cv;

using namespace cv::dnn;

using namespace std;

int main() {


	Net net = readNetFromCaffe("MobileNetSSD_deploy.prototxt", "MobileNetSSD_deploy.caffemodel");

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

	float detect_thresh = 0.24;
	VideoCapture cap("vtest.avi");
	if (!cap.isOpened()) return -1;
	while (true) {
		Mat frame;
		cap >> frame;

		if (frame.empty()) break;
		clock_t start_t = clock();
		//预测
		Mat inputblob = blobFromImage(frame, 1.0 / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
		net.setInput(inputblob, "data");
		Mat detetmat = net.forward("detection_out");

		cout << "Cost time: " << clock() - start_t << endl;
		//绘制
		Mat detectionMat(detetmat.size[2], detetmat.size[3], CV_32F, detetmat.ptr<float>());
		float confidence_th = 0.2;
		for (int i = 0; i < detectionMat.rows; i++) {

			//int obj_class = detectionMat.at<float>(i, 1);

			float confidence = detectionMat.at<float>(i, 2);

			if (confidence > confidence_th) {

				size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
				int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);

				int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);

				int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);

				int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);

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

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

				putText(frame, classNames[objectClass], Point(xLeftBottom, yLeftBottom - 10), 3, 0.5, Scalar(0, 0, 255), 2);

			}

		}


		imshow("test", frame);
		waitKey(50);
	}
	
	return 0;
}

 

detectionMat输入图像后经过网络前向传播后的输出7*10的结果矩阵，其定义盗用别人一张图来说明前向运行输出的图像结果矩阵，prob层的输出：实际意义为测试图片所对应与标签的概率值。resize成一个列向量，然后排序，输出最大值和最大值所对应的位置。

上图中置信概率最高(0.999)的目标数组下标为2，对应的是bicycle自行车，只要大于设置的阈值(变量confidenceThreshold)，就会在图像上标记出目标的位置(detectionMat行向量的3,4,5,6元素)。比如将阈值confidenceThreshold设置为0.5，则识别结果只有一个是大于0.5的，则只会在图像上标记出自行车，如下图：

参考博客：https://blog.****.net/KayChanGEEK/article/details/79978851

https://blog.****.net/samylee/article/details/80548323

https://blog.****.net/qq_15947787/article/details/78436995