VS+Opencv3.3下用HOG+SVM实现INRIA行人检测
2024-06-30 00:11:08
利用SVM训练一个分类器，用训练好的分类器对测试集里的数据进行检测。
这里是数据下载地址：INRIA行人数据集
点击页面下方的蓝色here即可下载。
下载完成之后，解压缩（为方便操作，建议放于项目目录下或者是根目录下，我这里是放在了D盘下面），进入文件夹，打开Train，有neg负样本，pos正样本。负样本的尺寸是437X292的，所以需要先处理一下，才能够进行训练。下面是处理代码（这里默认你已经配置好了opencv环境）。
#include <iostream>
#include <fstream>
#include <stdlib.h> //srand()和rand()函数
#include <time.h> //time()函数
#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; int CropImageCount = 0; //裁剪出来的负样本图片个数 int main()
{ Mat src; string ImgName; char saveName[256];//裁剪出来的负样本图片文件名 ifstream fin("D:/INRIAPerson/Train/neg.lst");//打开原始负样本图片文件列表 //一行一行读取文件列表 while(getline(fin,ImgName)) { cout<<"处理："<<ImgName<<endl; ImgName = "D:/INRIAPerson" + ImgName; src = imread(ImgName,1);//读取图片 //cout<<"宽："<<src.cols<<"，高："<<src.rows<<endl; //图片大小应该能能至少包含一个64*128的窗口 if(src.cols >= 64 && src.rows >= 128) { srand(time(NULL));//设置随机数种子 time(NULL)表示当前系统时间//从每张图片中随机采样10个64*128大小的不包含人的负样本 for(int i=0; i<10; i++) { int x = ( rand() % (src.cols-64) ); //左上角x坐标 int y = ( rand() % (src.rows-128) ); //左上角y坐标 //cout<<x<<","<<y<<endl; Mat imgROI = src(Rect(x,y,64,128)); sprintf(saveName,"D:/INRIAPerson/negphoto/noperson%06d.jpg",++CropImageCount);//生成裁剪出的负样本图片的文件名 imwrite(saveName, imgROI);//保存文件 } } } system("pause");
} 大概经过几十秒就能生成12000多张负样本的图片了。
接下来就是训练分类器以及对测试样本进行测试了。
#include "opencv2/core/core.hpp"
#include "opencv2/objdetect.hpp"
#include "opencv2/core/cuda.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/video/video.hpp"
#include "opencv2/ml.hpp"
#include "opencv2/opencv.hpp"
#include <opencv2/objdetect/objdetect.hpp>
#include <opencv2/imgcodecs.hpp>
#include <stdlib.h>
#include <time.h>
#include <algorithm>
#include <math.h>
#include <iostream>
#include <vector>
#include <fstream>
#include <cstdlib>
using namespace std;
using namespace cv;
using namespace cv::ml;//函数声明
void get_svm_detector(const Ptr< SVM > & svm, vector< float > & hog_detector);
void convert_to_ml(const std::vector< Mat > & train_samples, Mat& trainData);
void load_images(const String & dirname, vector< Mat > & img_lst, bool showImages);
void sample_neg(const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size);
void computeHOGs(const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst);
int test_trained_detector(String obj_det_filename, String test_dir, String videofilename);//函数定义
void get_svm_detector(const Ptr< SVM >& svm, vector< float > & hog_detector)
{// get the support vectorsMat sv = svm->getSupportVectors();const int sv_total = sv.rows;// get the decision functionMat alpha, svidx;double rho = svm->getDecisionFunction(0, alpha, svidx);CV_Assert(alpha.total() == 1 && svidx.total() == 1 && sv_total == 1); //括号中的条件不满足时，返回错误CV_Assert((alpha.type() == CV_64F && alpha.at<double>(0) == 1.) ||(alpha.type() == CV_32F && alpha.at<float>(0) == 1.f));CV_Assert(sv.type() == CV_32F);hog_detector.clear();hog_detector.resize(sv.cols + 1);memcpy(&hog_detector[0], sv.ptr(), sv.cols * sizeof(hog_detector[0])); //memcpy指的是c和c++使用的内存拷贝函数，memcpy函数的功能是从源src所指的内存地址的起始位置开始拷贝n个字节到目标dest所指的内存地址的起始位置中。hog_detector[sv.cols] = (float)-rho;
}/*
* Convert training/testing set to be used by OpenCV Machine Learning algorithms.
* TrainData is a matrix of size (#samples x max(#cols,#rows) per samples), in 32FC1.
* Transposition of samples are made if needed.
*/
void convert_to_ml(const vector< Mat > & train_samples, Mat& trainData)
{//--Convert dataconst int rows = (int)train_samples.size(); //行数等于训练样本个数const int cols = (int)std::max(train_samples[0].cols, train_samples[0].rows); //列数取样本图片中宽度与高度中较大的那一个Mat tmp(1, cols, CV_32FC1); //< used for transposition if neededtrainData = Mat(rows, cols, CV_32FC1);for (size_t i = 0; i < train_samples.size(); ++i){CV_Assert(train_samples[i].cols == 1 || train_samples[i].rows == 1);if (train_samples[i].cols == 1){transpose(train_samples[i], tmp);tmp.copyTo(trainData.row((int)i));}else if (train_samples[i].rows == 1){train_samples[i].copyTo(trainData.row((int)i));}}
}void load_images(const String & dirname, vector< Mat > & img_lst, bool showImages = false)
{ //载入目录下的图片样本vector< String > files;glob(dirname, files); //返回一个包含有匹配文件/目录的数组。出错则返回falsefor (size_t i = 0; i < files.size(); ++i){Mat img = imread(files[i]); // load the imageif (img.empty()) // invalid image, skip it.{cout << files[i] << " is invalid!" << endl;continue;}if (showImages){imshow("image", img);waitKey(1);}img_lst.push_back(img);//将Img压入img_lst}
}void sample_neg(const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size)
{ //该函数对每一个负样本采样出一个随机的64*128尺寸的样本，由于之前已经采样过了，所以main函数中没有使用该函数Rect box;box.width = size.width; //等于检测器宽度box.height = size.height; //等于检测器高度const int size_x = box.width;const int size_y = box.height;srand((unsigned int)time(NULL)); //生成随机数种子for (size_t i = 0; i < full_neg_lst.size(); i++){ //对每个负样本进行裁剪，随机指定x,y,裁剪一个尺寸为检测器大小的负样本box.x = rand() % (full_neg_lst[i].cols - size_x); box.y = rand() % (full_neg_lst[i].rows - size_y);Mat roi = full_neg_lst[i](box);neg_lst.push_back(roi.clone());}
}void computeHOGs(const Size wsize, const vector< Mat > & img_lst, vector< Mat > & gradient_lst)
{ //计算HOG特征HOGDescriptor hog;hog.winSize = wsize;Rect r = Rect(0, 0, wsize.width, wsize.height);r.x += (img_lst[0].cols - r.width) / 2; //正样本图片的尺寸减去检测器的尺寸，再除以2r.y += (img_lst[0].rows - r.height) / 2;Mat gray;vector< float > descriptors;for (size_t i = 0; i< img_lst.size(); i++){cvtColor(img_lst[i](r), gray, COLOR_BGR2GRAY);hog.compute(gray, descriptors, Size(8, 8), Size(0, 0)); //Size(8,8)为窗口移动步长，gradient_lst.push_back(Mat(descriptors).clone());}
}int test_trained_detector(String obj_det_filename, String test_dir, String videofilename)
{ //当videofilename为空，则只检测图片中的行人cout << "Testing trained detector..." << endl;HOGDescriptor hog;hog.load(obj_det_filename);vector< String > files;glob(test_dir, files);int delay = 0;VideoCapture cap;if (videofilename != ""){cap.open(videofilename);}obj_det_filename = "testing " + obj_det_filename;namedWindow(obj_det_filename, WINDOW_NORMAL);for (size_t i = 0;; i++){Mat img;if (cap.isOpened()){cap >> img;delay = 1;}else if (i < files.size()){img = imread(files[i]);}if (img.empty()){return 0;}vector< Rect > detections;vector< double > foundWeights;hog.detectMultiScale(img, detections, foundWeights);for (size_t j = 0; j < detections.size(); j++){if (foundWeights[j] < 0.5) continue; //清楚权值较小的检测窗口Scalar color = Scalar(0, foundWeights[j] * foundWeights[j] * 200, 0);rectangle(img, detections[j], color, img.cols / 400 + 1);}imshow(obj_det_filename, img);if (27 == waitKey(delay)){return 0;}}return 0;
}int main(int argc, char** argv)
{const char* keys ={"{help h| | show help message}""{pd | D:/INRIAPerson/96X160H96/Train/pos | path of directory contains possitive images}""{nd | D:/INRIAPerson/negphoto | path of directory contains negative images}""{td | D:/INRIAPerson/Test/pos | path of directory contains test images}""{tv | | test video file name}""{dw | 64 | width of the detector}""{dh | 128 | height of the detector}""{d |false| train twice}""{t |true| test a trained detector}""{v |false| visualize training steps}""{fn |D:/my_detector.yml| file name of trained SVM}"};CommandLineParser parser(argc, argv, keys); //命令行函数，读取keys中的字符， 其中key的格式为:名字 简称| 内容 |提示字符。if (parser.has("help")){parser.printMessage();exit(0);}String pos_dir = parser.get< String >("pd"); //正样本目录String neg_dir = parser.get< String >("nd"); //负样本目录String test_dir = parser.get< String >("td"); //测试样本目录String obj_det_filename = parser.get< String >("fn"); //训练好的SVM检测器文件名String videofilename = parser.get< String >("tv"); //测试视频int detector_width = parser.get< int >("dw"); //检测器宽度 int detector_height = parser.get< int >("dh"); //检测器高度bool test_detector = parser.get< bool >("t"); //测试训练好的检测器bool train_twice = parser.get< bool >("d"); //训练两次bool visualization = parser.get< bool >("v"); //训练过程可视化（建议false，不然爆炸)//根据评论，以下5行代码在初次运行时，请注释掉。该段代码是为了对已经训练好的模型进行测试的，初次运行时，因为还未有任何模型参数，所以可能会报错。//if (test_detector) //若为true，测对测试集进行测试//{// test_trained_detector(obj_det_filename, test_dir, videofilename);// exit(0);//}if (pos_dir.empty() || neg_dir.empty()) //检测非空{parser.printMessage();cout << "Wrong number of parameters.\n\n"<< "Example command line:\n" << argv[0] << " -pd=/INRIAPerson/96X160H96/Train/pos -nd=/INRIAPerson/neg -td=/INRIAPerson/Test/pos -fn=HOGpedestrian96x160.yml -d\n"<< "\nExample command line for testing trained detector:\n" << argv[0] << " -t -dw=96 -dh=160 -fn=HOGpedestrian96x160.yml -td=/INRIAPerson/Test/pos";exit(1);}vector< Mat > pos_lst, //正样本图片向量full_neg_lst, //负样本图片向量neg_lst, //采样后的负样本图片向量gradient_lst; //HOG描述符存入到该梯度信息里面vector< int > labels; //标签向量clog << "Positive images are being loaded...";load_images(pos_dir, pos_lst, visualization); //加载图片 pos正样本的尺寸为96*160if (pos_lst.size() > 0){clog << "...[done]" << endl;}else{clog << "no image in " << pos_dir << endl;return 1;}Size pos_image_size = pos_lst[0].size(); //令尺寸变量pos_image_size=正样本尺寸//检测所有正样本是否具有相同尺寸for (size_t i = 0; i < pos_lst.size(); ++i){if (pos_lst[i].size() != pos_image_size){cout << "All positive images should be same size!" << endl;exit(1);}}pos_image_size = pos_image_size / 8 * 8;//令pos_image_size的尺寸为检测器的尺寸if (detector_width && detector_height){pos_image_size = Size(detector_width, detector_height);}labels.assign(pos_lst.size(), +1); //assign()为labels分配pos_lst.size()大小的容器，用+1填充 表示为正样本const unsigned int old = (unsigned int)labels.size(); //旧标签大小clog << "Negative images are being loaded...";load_images(neg_dir, neg_lst, false); //加载负样本图片//sample_neg(full_neg_lst, neg_lst, pos_image_size); clog << "...[done]" << endl;labels.insert(labels.end(), neg_lst.size(), -1); //在labels向量的尾部添加neg_lst.size()大小的容器，用-1填充 表示为负样本CV_Assert(old < labels.size()); //CV_Assert()作用：CV_Assert（）若括号中的表达式值为false，则返回一个错误信息。clog << "Histogram of Gradients are being calculated for positive images...";computeHOGs(pos_image_size, pos_lst, gradient_lst); //计算正样本图片的HOG特征clog << "...[done]" << endl;clog << "Histogram of Gradients are being calculated for negative images...";computeHOGs(pos_image_size, neg_lst, gradient_lst); //计算负样本图片的HOG特征clog << "...[done]" << endl;Mat train_data;convert_to_ml(gradient_lst, train_data); //转化为ml所需的训练数据形式clog << "Training SVM...";Ptr< SVM > svm = SVM::create();/* Default values to train SVM */svm->setCoef0(0.0);svm->setDegree(3);svm->setTermCriteria(TermCriteria(CV_TERMCRIT_ITER + CV_TERMCRIT_EPS, 1000, 1e-3));svm->setGamma(0);svm->setKernel(SVM::LINEAR); //采用线性核函，其他的sigmoid 和RBF 可自行设置，其值由0-5。svm->setNu(0.5);svm->setP(0.1); // for EPSILON_SVR, epsilon in loss function?svm->setC(0.01); // From paper, soft classifiersvm->setType(SVM::EPS_SVR); // C_SVC; // EPSILON_SVR; // may be also NU_SVR; // do regression tasksvm->train(train_data, ROW_SAMPLE, Mat(labels));clog << "...[done]" << endl;//训练两次if (train_twice){clog << "Testing trained detector on negative images. This may take a few minutes...";HOGDescriptor my_hog;my_hog.winSize = pos_image_size;// Set the trained svm to my_hogvector< float > hog_detector;get_svm_detector(svm, hog_detector);my_hog.setSVMDetector(hog_detector);vector< Rect > detections;vector< double > foundWeights;for (size_t i = 0; i < full_neg_lst.size(); i++){my_hog.detectMultiScale(full_neg_lst[i], detections, foundWeights);for (size_t j = 0; j < detections.size(); j++){Mat detection = full_neg_lst[i](detections[j]).clone();resize(detection, detection, pos_image_size);neg_lst.push_back(detection);}if (visualization){for (size_t j = 0; j < detections.size(); j++){rectangle(full_neg_lst[i], detections[j], Scalar(0, 255, 0), 2);}imshow("testing trained detector on negative images", full_neg_lst[i]);waitKey(5);}}clog << "...[done]" << endl;labels.clear();labels.assign(pos_lst.size(), +1);labels.insert(labels.end(), neg_lst.size(), -1);gradient_lst.clear();clog << "Histogram of Gradients are being calculated for positive images...";computeHOGs(pos_image_size, pos_lst, gradient_lst);clog << "...[done]" << endl;clog << "Histogram of Gradients are being calculated for negative images...";computeHOGs(pos_image_size, neg_lst, gradient_lst);clog << "...[done]" << endl;clog << "Training SVM again...";convert_to_ml(gradient_lst, train_data);svm->train(train_data, ROW_SAMPLE, Mat(labels));clog << "...[done]" << endl;}vector< float > hog_detector; //定义hog检测器get_svm_detector(svm, hog_detector); //得到训练好的检测器HOGDescriptor hog;hog.winSize = pos_image_size; //窗口大小hog.setSVMDetector(hog_detector);hog.save(obj_det_filename); //保存分类器test_trained_detector(obj_det_filename, test_dir, videofilename); //检测训练集return 0;
}检测效果如下。这里使用的是线性核，有兴趣的可以自己改用其他核函数以及相关参数，感兴趣的可以在评论区一起讨论。
如果你觉得有用，帮忙扫个红包支持一下吧：
VS+Opencv3.3下用HOG+SVM实现INRIA行人检测相关推荐
- VS2017+Opencv4.2.0 用HOG+SVM实现INRIA行人检测 报错[ INFO:0] global
按照网上的代码用svm训练分类器 结果报错 [ INFO:0] global C:\build\master_winpack-build-win64-vc14\opencv\modules\core\ ...
- 用HOG+SVM在Inria数据集上做行人检测与评测
by baiyu33 功能 基于OpenCV在Inria行人检测数据集上,做训练和测试,生成bbs用于评测 代码 在OpenCV3.0中的例程opencv/sources/sample/cpp/tra ...
- python视频行人检测_python+opencv3.4.0 实现HOG+SVM行人检测的示例代码
参照opencv官网例程写了一个基于python的行人检测程序,实现了和自带检测器基本一致的检测效果. opencv版本:3.4.0 训练集和opencv官方用了同一个,可以从http://pasca ...
- 基于HOG特征的Adaboost行人检测
原地址:http://blog.csdn.net/van_ruin/article/details/9166591 1.方向梯度直方图(Histogramof Oriented Gradient, H ...
- 利用Hog特征和SVM分类器进行行人检测
1.HOG特征: 方向梯度直方图(Histogram of Oriented Gradient, HOG)特征是一种在计算机视觉和图像处理中用来进行物体检测的特征描述子.它通过计算和统计图像局部区域的 ...
- opencv roberts算子_图像之HOG特征描述算子-行人检测
4.1 简介 本次任务将学习一种在深度学习之前非常流行的图像特征提取技术--方向梯度直方图(Histogram of Oriented Gradients),简称HOG特征.HOG特征是在2005年C ...
- CV之 HOG特征描述算子-行人检测
4.1 简介 本次任务将学习一种在深度学习之前非常流行的图像特征提取技术--方向梯度直方图(Histogram of Oriented Gradients),简称HOG特征.HOG特征是在2005年C ...
- Win10环境下CPU版本基于YOLOv5的行人检测研究（包括Anaconda安装超详细）
安装Anaconda 直达链接Anaconda 点击get started 点击Download Anaconda Installers 点击Download 然后保存执行文件即可 开始安装Anaco ...
- HOG+SVM实现行人检测
一.概述 行人检测过去流行采用的方法是DPM方法,其主要采用hog特征+SVM分类实现行人检测: 其中梯度方向直方图( Histogram of Oriented Gradients,HOG)的概念是 ...
最新文章
- oracle 11g asm 磁盘组兼容属性
- leetcode算法题--有序数组中的单一元素
- 微信小程序注意点及快捷键
- HiveDuino开发套件
- hdu 5367(线段树+区间合并)
- 如何编写nopCommerce插件
- [原]全桥移相(PSFB)原边电流突跌分析
- python之集合与字典
- corn表达式的简单使用
- 《大前端进阶 安全》系列 HTTPS详解（通俗易懂）
- 【电商运营】京东数字化运营【客单价篇】
- 为什么我无法访问自己的工作组Workgroup
- CentOS 搭建NFS
- python输入单个字符_关于输入：Python从用户读取单个字符
- 中国象棋c语言源代码csdn,中国象棋源代码-C语言小程序
- App是什么，可以分为几类？及其相关解释。
- STL之set map 和multiset multimap理解
- SylixOS更新记录
- java months between,ORACLE函数MONTHS_BETWEEN
- Intellij IDEA 干货分享