锐客网

  1. 首页 > 睿知 > it技术 > >

HOG+SVM实现行人检测 行人检测（带hard样本）

IT知识检测行人检测

万事须己运，他得非我贤。这篇文章主要讲述HOG+SVM实现行人检测 行人检测（带hard样本）相关的知识，希望能为你提供帮助。
【HOG+SVM实现行人检测 行人检测（带hard样本）】1，示例代码

#include
#include
#include
#include
#include
#include
#include
#include

using namespace std;
using namespace cv;
using namespace cv::ml;


#define PosSamNO 2416//原始正样本数
#define NegSamNO 6070 // 剪裁后的负样本数6070
#define cropNegNum 1214//原始负样本数

#define HardExampleNO 10896 // hard negative num//10896
#define AugPosSamNO 0 //Aug positive num

#define TRAIN true //是否进行训练,true表示重新训练，false表示读取xml文件中的SVM模型
#define CENTRAL_CROP true //true:训练时，对96*160的INRIA正样本图片剪裁出中间的64*128大小人体
#define crop_negsample true //随机剪裁负样本数的开关

/*********************************随机剪裁负样本*******************************************/
void crop_negsample_random()

string imgName;
char saveName[200];
//读入文件txt名
ifstream fileNeg("/Users/macbookpro/CLionProjects/pedestrian_detection/img_dir/sample_neg.txt");

int num=0;
//如果文件存在，则先删除该文件
//写入文件txt名
ofstream fout("/Users/macbookpro/CLionProjects/pedestrian_detection/img_dir/sample_new_neg.txt",ios::trunc); //加路径

//读取负样本
//当i小于负样本数量，进行循环，同时读入文件fileNeg中值到imgName中
for (int i = 0; i < cropNegNum & & getline(fileNeg, imgName); i++)

imgName = "/Users/macbookpro/CLionProjects/pedestrian_detection/normalized_images/train/neg/" + imgName;
//IMREAD_UNCHANGED ：不进行转化，比如保存为了16位的图片，读取出来仍然为16位。
Mat img = imread(imgName, IMREAD_UNCHANGED);
//Linux时间函数
//tv_sec; /* Seconds. */
//tv_usec; /* Microseconds. */
struct timeval tv;
if (img.empty())//如果图片不存在，则输出

cout < < "can not load the image:" < < imgName < < endl;
continue;

if (img.cols > = 64 & & img.rows > = 128)//如果图片尺寸大于64或者128时

num = 0;
//从每张图片中随机剪裁5(10)张64*128的负样本
for (int j = 0; j < 5; j++)


//gettimeofday()会把目前的时间用tv 结构体返回
gettimeofday(& tv,NULL);
srand(tv.tv_usec); //利用系统时间（微妙），设置随机数种子

int x = rand() % (img.cols - 64); //左上角x， 范围为[0,cols - 64)
int y = rand() % (img.rows - 128); //左上角y， 范围为[0,rows - 64)
cout < < "x:" < < x < < "y:" < < y < < endl;
Mat src = https://www.songbingjia.com/android/img(Rect(x, y, 64, 128)); //Rect(x,y,64,128)从左上角坐标为(x,y)位置剪裁一个宽64，高128的矩形
//把剪裁后的图片名称存入svaeName变量中
sprintf(saveName, "/Users/macbookpro/CLionProjects/pedestrian_detection/normalized_images/train/new_neg/neg%dCropped%d.png",i, num);
//把剪裁后的图片src，另存为名字为svaeName的图片
imwrite(saveName,src);

//保存裁剪得到的图片名称到txt文件，换行分隔
if(i< (cropNegNum-1))
fout < < "neg" < < i < < "Cropped"< < num++ < < ".png"< < endl;

else if(i==(cropNegNum-1) & & j< 4)
fout < < "neg" < < i < < "Cropped"< < num++ < < ".png"< < endl;

else
fout < < "neg" < < i < < "Cropped"< < num++ < < ".png";




fout.close(); //关闭文件
cout < < "crop ok!" < < endl;


int main()

if(crop_negsample)
// crop_negsample_random(); //裁剪负样本

//检测窗口(64,128),块尺寸(16,16),块步长(8,8),cell尺寸(8,8),直方图bin个数9
HOGDescriptor hog(Size(64,128),Size(16,16),Size(8,8),Size(8,8),9);
int DescriptorDim; //HOG描述子的维数，由图片大小、检测窗口大小、块大小、细胞单元中直方图bin个数决定
Ptr< SVM> svm = SVM::create(); // 创建分类器

if(TRAIN)//若TRAIN为true，重新训练分类器

string ImgName; //图片名(绝对路径)
//正样本图片的文件名列表
ifstream finPos("/Users/macbookpro/CLionProjects/pedestrian_detection/img_dir/sample_pos.txt");
// ifstream finNeg("../sample_neg.txt");
//负样本图片的文件名列表
ifstream finNeg("/Users/macbookpro/CLionProjects/pedestrian_detection/img_dir/sample_new_neg.txt");
//HardExample负样本的文件名列表
ifstream finHardNeg("/Users/macbookpro/CLionProjects/pedestrian_detection/img_dir/hard_neg.txt");

//if (!finPos || !finNeg || !finHardNeg)
if (!finPos || !finNeg)

cout < < "Pos/Neg/hardNeg imglist reading failed..." < < endl;
return 1;


Mat sampleFeatureMat;
Mat sampleLabelMat;

//loading original positive examples...
for(int num=0; num < PosSamNO & & getline(finPos,ImgName); num++)

cout < < "Now processing original positive image: " < < ImgName < < endl;
ImgName = "/Users/macbookpro/CLionProjects/pedestrian_detection/normalized_images/train/pos/" + ImgName;
Mat src = https://www.songbingjia.com/android/imread(ImgName); //读取图片

if(CENTRAL_CROP)//true:训练时，对96*160的INRIA正样本图片剪裁出中间的64*128大小人体
if(src.cols > = 96 & & src.rows > = 160)
//resize(src,src,Size(64,128));
src = https://www.songbingjia.com/android/src(Rect(16,16,64,128));
// else cout < < "error" < < endl; //测试

vector< float> descriptors; //HOG描述子向量
hog.compute(src, descriptors, Size(8,8)); //计算HOG描述子，检测窗口移动步长(8,8)
//cout< < "描述子维数："<


//处理第一个样本时初始化特征向量矩阵和类别矩阵，因为只有知道了特征向量的维数才能初始化特征向量矩阵
if(num == 0 )

DescriptorDim = descriptors.size(); //HOG描述子的维数
//初始化所有训练样本的特征向量组成的矩阵，行数等于所有样本的个数，列数等于HOG描述子维数sampleFeatureMat
sampleFeatureMat = Mat::zeros(PosSamNO +AugPosSamNO +NegSamNO +HardExampleNO, DescriptorDim, CV_32FC1); //CV_32FC1：CvMat数据结构参数
//初始化训练样本的类别向量，行数等于所有样本的个数，列数等于1；1表示有人，0表示无人
sampleLabelMat = Mat::zeros(PosSamNO +AugPosSamNO +NegSamNO +HardExampleNO, 1, CV_32SC1); //sampleLabelMat的数据类型必须为有符号整数型


//将计算好的HOG描述子复制到样本特征矩阵sampleFeatureMat
for(int i=0; i< DescriptorDim; i++)
sampleFeatureMat.at< float> (num,i) = descriptors[i]; //第num个样本的特征向量中的第i个元素
sampleLabelMat.at< int> (num,0) = 1; //正样本类别为1，有人

finPos.close();


//依次读取负样本图片，生成HOG描述子
for(int num = 0; num < NegSamNO & & getline(finNeg,ImgName); num++)

cout< < "Now processing original negative image: "< < ImgName< < endl;
// ImgName = "../normalized_images/train/neg/" + ImgName;
//加上负样本的路径名
ImgName = "/Users/macbookpro/CLionProjects/pedestrian_detection/normalized_images/train/new_neg/" + ImgName;
Mat src = https://www.songbingjia.com/android/imread(ImgName); //读取图片

vector< float> descriptors; //HOG描述子向量
hog.compute(src,descriptors,Size(8,8)); //计算HOG描述子，检测窗口移动步长(8,8)

//将计算好的HOG描述子复制到样本特征矩阵sampleFeatureMat
for(int i=0; i< DescriptorDim; i++)
sampleFeatureMat.at< float> (num+PosSamNO+AugPosSamNO,i) = descriptors[i]; //第PosSamNO+num个样本的特征向量中的第i个元素
sampleLabelMat.at< int> (num +PosSamNO +AugPosSamNO, 0) = -1; //负样本类别为-1，无人


finNeg.close();

//依次读取HardExample负样本图片，生成HOG描述子
for(int num = 0; num < HardExampleNO & & getline(finHardNeg,ImgName); num++)

cout< < "Now processing original hard negative image: "< < ImgName< < endl;
// ImgName = "../normalized_images/train/neg/" + ImgName;
//加上负样本的路径名
ImgName = "/Users/macbookpro/CLionProjects/pedestrian_detection/normalized_images/train/hard_neg/" + ImgName;
Mat src = https://www.songbingjia.com/android/imread(ImgName); //读取图片

vector< float> descriptors; //HOG描述子向量
hog.compute(src,descriptors,Size(8,8)); //计算HOG描述子，检测窗口移动步长(8,8)
//cout< < "描述子维数："<

//将计算好的HOG描述子复制到样本特征矩阵sampleFeatureMat
for(int i=0; i< DescriptorDim; i++)
sampleFeatureMat.at< float> (num+ PosSamNO + NegSamNO + AugPosSamNO,i) = descriptors[i]; //第PosSamNO+num个样本的特征向量中的第i个元素
sampleLabelMat.at< int> (num + PosSamNO + NegSamNO + AugPosSamNO, 0) = -1; //负样本类别为-1，无人


finHardNeg.close();



svm -> setType(SVM::C_SVC);
svm -> setC(0.01);
svm -> setKernel(SVM::LINEAR);
// svm -> setTermCriteria(TermCriteria(TermCriteria::MAX_ITER, 3000, 1e-6));
svm -> setTermCriteria(TermCriteria(TermCriteria::MAX_ITER, 100, 1e-3));

cout< < "Starting training..."< < endl;
svm -> train(sampleFeatureMat, ROW_SAMPLE, sampleLabelMat);
cout< < "Finishing training..."< < endl;

svm -> save("/Users/macbookpro/CLionProjects/pedestrian_detection/data/SVM_HOG.xml");


else
svm = SVM::load( "/Users/macbookpro/CLionProjects/pedestrian_detection/data/SVM_HOG_2.xml" );

cout < < "loaded SVM_HOG.xml file"< < endl;

int svdim = svm -> getVarCount(); //特征向量的维数，即HOG描述子的维数
//支持向量的个数
Mat svecsmat = svm -> getSupportVectors(); //svecsmat元素的数据类型为float
int numofsv = svecsmat.rows;

// Mat alphamat = Mat::zeros(numofsv, svdim, CV_32F); //alphamat和svindex必须初始化，否则getDecisionFunction()函数会报错
Mat alphamat = Mat::zeros(numofsv, svdim, CV_32F);
Mat svindex = Mat::zeros(1, numofsv,CV_64F);
cout < < "after initialize the value of alphamat is" < < alphamat.size()< < endl;

Mat Result;
double rho = svm -> getDecisionFunction(0, alphamat, svindex);

cout < < "the value of rho is" < < rho < < endl;
alphamat.convertTo(alphamat, CV_32F); //将alphamat元素的数据类型重新转成CV_32F
cout < < "the value of alphamat is" < < alphamat < < endl;
cout < < "the size of alphamat is" < < alphamat.size() < < endl;
cout < < "the size of svecsmat is" < < svecsmat.size() < < endl;

//计算-(alphaMat * supportVectorMat),结果放到resultMat中
Result = -1 * alphamat * svecsmat; //float

cout < < "the value of svdim is" < < svdim < < endl;

//得到最终的setSVMDetector(const vector& detector)参数中可用的检测子
vector< float> vec;
//将resultMat中的数据复制到数组vec中
for (int i = 0; i < svdim; ++i)

vec.push_back(Result.at< float> (0, i));

vec.push_back(rho);

cout < < "going to write the HOGDetectorForOpenCV.txt file"< < endl;
//saving HOGDetectorForOpenCV.txt
ofstream fout("/Users/macbookpro/CLionProjects/pedestrian_detection/data/HOGDetectorForOpenCV.txt");
for (int i = 0; i < vec.size(); ++i)

fout < < vec[i] < < endl;

fout.close(); //关闭文件


/*********************************Testing**************************************************/
HOGDescriptor hog_test;
hog_test.setSVMDetector(vec);

// Mat src = https://www.songbingjia.com/android/imread("../person_and_bike_177b.png");
Mat src = https://www.songbingjia.com/android/imread("/Users/macbookpro/CLionProjects/pedestrian_detection/data/Test.jpg");
vector< Rect> found, found_filtered;
hog_test.detectMultiScale(src, found, 0, Size(8,8), Size(32,32), 1.05, 2);

cout< < "found.size : "< < found.size()< < endl;

//找出所有没有嵌套的矩形框r,并放入found_filtered中,如果有嵌套的话,则取外面最大的那个矩形框放入found_filtered中
for(int i=0; i < found.size(); i++)

Rect r = found[i];
int j=0;
for(; j < found.size(); j++)
if(j != i & & (r & found[j]) == r)
break;
if( j == found.size())
found_filtered.push_back(r);



//画矩形框，因为hog检测出的矩形框比实际人体框要稍微大些,所以这里需要做一些调整
for(int i=0; i< found_filtered.size(); i++)

Rect r = found_filtered[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(src, r.tl(), r.br(), Scalar(0,255,0), 3);


imwrite("ImgProcessed.jpg",src);
namedWindow("src",0);
imshow("src",src);
waitKey(0);

/******************读入单个64*128的测试图并对其HOG描述子进行分类*********************/
读取测试图片(64*128大小)，并计算其HOG描述子
//Mat testImg = imread("person014142.jpg");
//Mat testImg = imread("noperson000026.jpg");
//vector descriptor;
//hog.compute(testImg,descriptor,Size(8,8)); //计算HOG描述子，检测窗口移动步长(8,8)
//Mat testFeatureMat = Mat::zeros(1,3780,CV_32FC1); //测试样本的特征向量矩阵
//将计算好的HOG描述子复制到testFeatureMat矩阵中
//for(int i=0; i
//testFeatureMat.at(0,i) = descriptor[i];

//用训练好的SVM分类器对测试图片的特征向量进行分类
//int result = svm.predict(testFeatureMat); //返回类标
//cout< < "分类结果："<

return 0;

 



    推荐阅读


    上一篇：领歌敏捷协作——添加泳道，列表和快速移动技巧

    下一篇：领歌敏捷协作——创建看板