Opencv中HOG+SVM进行行人检测

来源：互联网发布：js 父窗口 span 编辑：程序博客网时间：2024/04/28 18:09

一.基本函数介绍：

1.HOG特征提取：cv::HOGDescriptor类

CV_WRAP HOGDescriptor() :      winSize(64,128),                             // detect window       blockSize(16,16),                            // block 大小       blockStride(8,8),                            // overlap block的滑动步长       cellSize(8,8),                               // cell 大小        nbins(9),                                    // 直方图的bin个数       derivAperture(1),                            // 微分算子核       winSigma(-1),                                // 在window上进行高斯加权       histogramNormType(HOGDescriptor::L2Hys),     // 直方图归一化类型       L2HysThreshold(0.2),                         // L2 norm followed by clipping(limiting maximum values  of v to 0.                                                   2) and renormalising   gammaCorrection(true),                       // Gamma校正，去除光照影响      nlevels(HOGDescriptor::DEFAULT_NLEVELS)      // 分层数

2.一个window内HOG特征的维数计算：

(1) block的个数：

blockNum=[(winSize.x-blockStride.x)/blockStride.x+1]*[(winSize.y - blockStride.y)/blockStride.y+1]

(2) 一个block中特征维数：

featuresPerBlock = ( blockSize.x/cellSize.x)*( blockSize.y/cellSize.y)*nbins

(3) window内HOG特征维数：

blockNum*featuresPerBlock则按上面默认参数计算，一个window内维数应该为3780维。

3.HOG特征提取源代码：

#include#include#include#include "opencv2\opencv.hpp"#define IMG_PATH "D:\\1.jpg"//图片路径using namespace std;int main(void) {    cout << "hi!" << endl;    cv::Mat mat = cv::imread(IMG_PATH);     cout<<"width:"<<mat.cols<<" height:"<<mat.rows<<endl; //显示图片大小    // 显示原图像    cv::namedWindow("Image", CV_WINDOW_AUTOSIZE);    cv::moveWindow("Image", 0, 0);    cv::imshow("Image", mat);    cv::HOGDescriptor hog;    vector descriptors;    hog.compute(mat, descriptors);    cout<<"size of HOG:"<<descriptors.size()<<endl;  //显示图片提取的总的HOG特征维数    cout << "finished." << endl;    cv::waitKey(0);    cout << "bye." << endl;    return EXIT_SUCCESS;}

二.HOG和SVM结合进行检测
1.HOG和SVM结合：
HOGDescriptor::setSVMDetector(const vector& detector)其中 const vector& detector 在 opencv 中有已经训练好的行人检测分类器，直接用：            HOGDescriptor::getDefaultPeopleDetector            HOGDescriptor::getPeopleDetector48x96            HOGDescriptor::getPeopleDetector64x128
 
2.对输入图像进行检测：
(1) 方法一：只在一个尺度上(即原图像上进行检测)
原型：HOGDescriptor::detect(const Mat& img, vector& found_locations, double hit_threshold=0, Size win_stride=Size(), Size padding=Size())参数解释：img – Source image. CV_8UC1 and CV_8UC4 types are supported for now.
found_locations – Left-top corner points of detected objects boundaries.
hit_threshold – Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specfied in the detector coefficients (as the last free coefficient). But if the free coefficient is omitted (which is allowed), you can specify it manually here.
win_stride – Window stride. It must be a multiple of block stride.
padding – Mock parameter to keep the CPU interface compatibility. It must be (0,0).
 
(2) 方法二：(在多个尺度上进行检测)
原型：HOGDescriptor::detectMultiScale(const　Mat& img, vector& found_locations, doublehit_threshold=0, Size win_stride=Size(), Size padding=Size(), double scale0=1.05, int group_threshold=2)参数解释：img – Source image. See HOGDescriptor::detect() for type limitations.
found_locations – Detected objects boundaries.
hit_threshold – Threshold for the distance between features and SVM classifying plane. SeeHOGDescriptor::detect() for details.
win_stride – Window stride. It must be a multiple of block stride.
padding – Mock parameter to keep the CPU interface compatibility. It must be (0,0).
scale0 – Coefficient of the detection window increase.
group_threshold – Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping. See groupRectangles()，说白了就是一个目标上覆盖有多个框的时候，通过设置该参数能去重(overlap)。
 
3.在图像上进行检测源代码
（参考了http://blog.csdn.net/icvpr/article/details/8454439的代码）
#include <iostream>   #include <opencv2/opencv.hpp>   #include <opencv2/core/core.hpp>#include <opencv2/highgui/highgui.hpp>#include "opencv2/objdetect/objdetect.hpp" int main()  {          cv::Mat image = cv::imread("test.bmp");          if (image.empty())          {               std::cout<<"read image failed"<<std::endl;           }          // 定义HOG对象               cv::HOGDescriptor hog; // 采用默认参数           //  设置SVM分类器   采用已经训练好的行人检测分类器               hog.setSVMDetector(cv::HOGDescriptor::getDefaultPeopleDetector());           // 3. 在测试图像上检测行人区域               std::vector regions;  //存储返回的矩形框结果        // 在对尺度上对Image进行检测            hog.detectMultiScale(image, regions, 0, cv::Size(8,8), cv::Size(32,32), 1.05, 1);           // 显示检测后的结果           for (size_t i = 0; i < regions.size(); i++)           {                  cv::rectangle(image, regions[i], cv::Scalar(0,0,255), 2);           }             cv::imshow("hog", image);             cv::waitKey(0);             return 0;   }  
 
 4.可能出错的地方：
 (1) hog.setSVMDetector(cv::HOGDescriptor::getDefaultPeopleDetector());   改为：static vector detector = HOGDescriptor::getDefaultPeopleDetector();if (!detector.size()){       fprintf(stderr, "ERROR: getDefaultPeopleDetector returned NULL\n");       return -1;     }hog.setSVMDetector(detector);
 
最后一个相关内容的比较好的英文网址：http://docs.opencv.org/modules/gpu/doc/object_detection.html

0 0