opencv角点检测android,基于opencv的角点检测

OpenCV角点检测小结

1，cvGoodFeaturesToTrack，cvCornerMinEigenVal，CornerEigenValsAndVecs是一类，用到了图像差分的相关矩阵。

2，CornerHarris，利用CornerEigenValsAndVecs得到的图像差分相关矩阵，据其特征值和向量，判断角点，   Harris角点探测器R(x，y)=det(M)-k*trace^2(M)

3，FindCornerSubPix，子象素级角点定位的实现是基于对向量正交性的观测而实现的。貌似适合棋盘格特征点检测，有待研究。

4，cvPreCornerDetect，计算一个二阶导多项式，角点被认为是函数的局部最大值。其实就是K-R法，利用了梯度的变化率在边缘走   向的投影能反映尖锐程度。试验发现是一种比cvGoodFeaturesToTrack粗略的办法。

注意：1，2，4都是检测像素级的角点。

#include "stdafx.h"

#include "cv.h"

#include "highgui.h"

#include "cxcore.h"

#define max_corners 500

int _tmain(int argc, _TCHAR* argv[])

{

int cornerCount=max_corners;

CvPoint2D32f corners[max_corners];

double qualityLevel;

double minDistance;

IplImage *srcImage = 0, *grayImage = 0, *corners1 = 0, *corners2 = 0;

int i;

CvScalar color = CV_RGB(255,0,0);

cvNamedWindow( "image", 1 ); // create HighGUI window with name "image"

//Load the image to be processed

srcImage = cvLoadImage("D://zero//VasoR.bmp",1);

grayImage = cvCreateImage(cvGetSize(srcImage), IPL_DEPTH_8U, 1);

//copy the source image to copy image after converting the format

cvCvtColor(srcImage, grayImage, CV_BGR2GRAY);

//create empty images of same size as the copied images

corners1= cvCreateImage(cvGetSize(srcImage), IPL_DEPTH_32F, 1);

corners2= cvCreateImage(cvGetSize(srcImage),IPL_DEPTH_32F, 1);

cvGoodFeaturesToTrack (grayImage, corners1, corners2, corners,

&cornerCount, 0.05, 5, 0);

printf("num corners found: %d/n", cornerCount);

// draw circles at each corner location in the gray image and

// print out a list the corners

if(cornerCount>0)

{

for (i=0; i

{

cvCircle(srcImage, cvPoint((int)(corners[i].x), (int)(corners[i].y)), 1,

color, 2, CV_AA, 0);

}

}

cvShowImage( "image", srcImage );

cvWaitKey(0); // wait for key. The function has

cvDestroyWindow("image");

cvReleaseImage(&srcImage);

cvReleaseImage(&grayImage);

cvReleaseImage(&corners1);

cvReleaseImage(&corners2);

return 0;

}