以前做算法实现一直用的说matlab,最近做目标跟踪的算法,开始使用Opencv,发现Opencv真的很强大,集合了很多算法,封装了很多函数,使用方法跟matlab很类似,但又比matlab的效率高。下面说我使用hog算法进行人体检测的代码,跟Opencv中的peopledetect.cpp类似,不过我修改了一些代码,可以检测连续的视频序列。
代码如下:
#include <fstream> #include <string> #include <cv.h> #include <highgui.h> #include <ml.h> #include <iostream> #include <fstream> #include <string> #include <vector> #include "cvaux.h" #include <iostream> #include <stdio.h> #include <string.h> #include <ctype.h> using namespace cv; using namespace std; int main() { Mat img0,img1; Mat img2; //Mat img3; int i; FILE* f = 0; char _filename[1024]; //imshow("hello",img3); //waitKey(0); HOGDescriptor hog; //CvLatentSvmDetector* detector = cvLoadLatentSvmDetector("result.xml"); CvSVM svm; svm.load("result.xml"); //hog.load("result.xml"); //int sv_num= svm.get_support_vector_count(); hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector()); //hog.setSVMDetector(detector); Mat img4; for(i=46;i<180;i++) { char file[1024]; sprintf(file,"D:\\My Documents\\Visual Studio 2008\\Projects\\cc\\CS-%d.bmp",i); char file4[1024]; sprintf(file4,"D:\\My Documents\\Visual Studio 2008\\Projects\\cc\\CS-%d.bmp",i-1); Mat img3; img3 = imread(file4); img4 = imread(file,1); //cvSub((CvMat)img2,(CvMat)img3,img); //img = img4-img3; Mat img(img4.rows,img4.cols,CV_8UC1); for(int n=0;n<img4.rows;n++) { for(int j=0;j<img4.cols;j++) { short e,d; short temp; e = *(img4.data+n*img4.step+j*3); d = *(img3.data+n*img3.step+j*3); //c = *(img2.data+i); temp = e-d; if(abs(temp)<3) temp=0; *(img.data+n*img.step+j) = (uchar)e; } } //cv::subtract //char* filename = _filename; char* filename = file; if(0) { if(!fgets(filename, (int)sizeof(_filename)-2, f)) break; //while(*filename && isspace(*filename)) // ++filename; if(filename[0] == '#') continue; int l = strlen(filename); while(l > 0 && isspace(filename[l-1])) --l; filename[l] = '\0'; img = imread(filename); } printf("%s:\n", filename); if(!img.data) continue; fflush(stdout); vector<Rect> found, found_filtered; double t = (double)getTickCount(); // run the detector with default parameters. to get a higher hit-rate // (and more false alarms, respectively), decrease the hitThreshold and // groupThreshold (set groupThreshold to 0 to turn off the grouping completely). int can = img.channels(); hog.detectMultiScale(img, found, 0, Size(8,8), Size(32,32), 1.05, 2); t = (double)getTickCount() - t; printf("tdetection time = %gms\n", t*1000./cv::getTickFrequency()); size_t i, j; for( i = 0; i < found.size(); i++ ) { Rect r = found[i]; for( j = 0; j < found.size(); j++ ) if( j != i && (r & found[j]) == r) break; if( j == found.size() ) found_filtered.push_back(r); } for( i = 0; i < found_filtered.size(); i++ ) { Rect r = found_filtered[i]; // the HOG detector returns slightly larger rectangles than the real objects. // so we slightly shrink the rectangles to get a nicer output. r.x += cvRound(r.width*0.1); r.width = cvRound(r.width*1); r.y += cvRound(r.height*0.07); r.height = cvRound(r.height*0.8); rectangle(img, r.tl(), r.br(), cv::Scalar(0,255,0), 3); } imshow("people detector", img); //int c = waitKey(0) & 255; //if( c == 'q' || c == 'Q' || !f) //break; waitKey(1); //cvDestoryWindow("people detector"); } if(f) fclose(f); return 0; }
其中hog.setSVMDetector(HOGDescriptor::getDefaultPeopleDetector());得到svm的检测算子。
hog.detectMultiScale(img, found, 0, Size(8,8), Size(32,32), 1.05, 2);得到检测的结果。