載入訓練好的行人分類器，實現行人檢測功能。

程式碼中用到的訓練好的行人分類器"pedestrianDetect.xml"下載路徑：https://download.csdn.net/download/lyq_12/10742144

一、效果如下：

1、輸入原圖

2、輸出結果

二、程式碼實現如下：

#include <iostream>
#include <fstream>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/objdetect/objdetect.hpp>
#include <opencv2/ml/ml.hpp>
 
using namespace std;
using namespace cv;
 
class MySVM : public CvSVM
{
public:
	//獲得SVM的決策函式中的alpha陣列
	double * get_alpha_vector()
	{
		return this->decision_func->alpha;
	}
 
	//獲得SVM的決策函式中的rho引數,即偏移量
	float get_rho()
	{
		return this->decision_func->rho;
	}
};
 
 
int main()
{
	MySVM svm;                          //SVM分類器
	svm.load("pedestrianDetect.xml");	//載入訓練好的行人分類器
	
	int DescriptorDim = svm.get_var_count();                //特徵向量的維數，即HOG描述子的維數
	int supportVectorNum = svm.get_support_vector_count();  //支援向量的個數
	//cout<<"支援向量個數："<<supportVectorNum<<endl;
 
	Mat alphaMat = Mat::zeros(1, supportVectorNum, CV_32FC1);                      
	Mat supportVectorMat = Mat::zeros(supportVectorNum, DescriptorDim, CV_32FC1);  
	Mat resultMat = Mat::zeros(1, DescriptorDim, CV_32FC1);                        
 
	for(int i=0; i<supportVectorNum; i++)
	{
		const float * pSVData = svm.get_support_vector(i); 
		for(int j=0; j<DescriptorDim; j++)
		{
			supportVectorMat.at<float>(i,j) = pSVData[j];
		}
	}
 
	double * pAlphaData = svm.get_alpha_vector();       
	for(int i=0; i<supportVectorNum; i++)
	{
		alphaMat.at<float>(0,i) = pAlphaData[i];
	}
 
	resultMat = -1 * alphaMat * supportVectorMat;
 
	vector<float> myDetector;
	for(int i=0; i<DescriptorDim; i++)
	{
		myDetector.push_back(resultMat.at<float>(0,i));
	}

	myDetector.push_back(svm.get_rho());
	//cout<<"檢測子維數："<<myDetector.size()<<endl;

	HOGDescriptor myHOG;
	myHOG.setSVMDetector(myDetector);	   //設定HOGDescriptor的檢測子
  
	Mat srcImg = imread("..\\srcImg.jpg");
	if (srcImg.empty())
	{
		cout<<"Failed to read image.";
		return -1;
	}

	//resize(srcImg, srcImg, Size(288,216));
	imshow("srcImg", srcImg);

	vector<Rect> detectRects, detectRectsAfterNMS;    //儲存檢測結果
	Mat dstImg = srcImg.clone();
	myHOG.detectMultiScale(dstImg, detectRects, 0, Size(8,8), Size(32,32), 1.05, 2);   //對輸入圖片進行行人檢測
	 
	//對detectRects進行非極大值抑制
	for(int i=0; i < detectRects.size(); i++)
	{
		Rect r = detectRects[i];
		int j=0;
		for(; j < detectRects.size(); j++)
		{
			if(j != i && (r & detectRects[j]) == r)
			{
				break;
			}
		}
		if( j == detectRects.size())
		{
			detectRectsAfterNMS.push_back(r);
		}
	}
 
	//畫出NMS之後的行人檢測結果
	for(int i=0; i<detectRectsAfterNMS.size(); i++)
	{
		Rect r = detectRectsAfterNMS[i];
		r.x += cvRound(r.width*0.1);
		r.width = cvRound(r.width*0.8);
		r.y += cvRound(r.height*0.07);
		r.height = cvRound(r.height*0.8);
		rectangle(dstImg, r.tl(), r.br(), Scalar(0,255,0), 3);
	}

	imshow("dstImg",dstImg);
	waitKey(0);
}
 

參考資料：https://blog.csdn.net/masibuaa/article/details/16105073?utm_source=tuicool&utm_medium=referral