Surf算法学习心得(三)——Demo分析

 

OpenCV Demo分析（find_obj.cpp）

OpenCV2.1中有关于 Surf算法的简单示例(1.1以上的版本都添加了这个算法)，在路径：C:\Program Files\OpenCV2.1\samples\c下，名为find_obj.cpp，运行它可以直接观察到相应结果。为了便于介绍这个示例，简单做了如下修改（只是删掉一些代码，但是对于如何使用 Surf算法没有影响）。

修改后的代码及其注释如下：（主要是介绍这个main函数）

/*

* A Demo to OpenCV Implementation of SURF

* Further Information Refer to “ SURF: Speed-Up Robust Feature”

* Author: Liu Liu

* [e-mail]

*/

#include “stdafx.h”

#include <cv.h>

#include <highgui.h>

#include <ctype.h>

#include <stdio.h>

#include <stdlib.h>

#include <iostream>

#include <vector>

using namespace std;

IplImage *image = 0;

double compare SURFDescriptors( const float* d1, const float* d2, double best, int length )

{

double total_cost = 0;

assert( length % 4 == 0 );

for( int i = 0; i < length; i += 4 )

{

double t0 = d1[i] – d2[i];

double t1 = d1[i+1] – d2[i+1];

double t2 = d1[i+2] – d2[i+2];

double t3 = d1[i+3] – d2[i+3];

total_cost += t0*t0 + t1*t1 + t2*t2 + t3*t3;

if( total_cost > best )

break;

}

return total_cost;

}

int naiveNearestNeighbor( const float* vec, int laplacian,

const CvSeq* model_keypoints,

const CvSeq* model_descriptors )

{

int length = (int)(model_descriptors->elem_size/sizeof(float));

int i, neighbor = -1;

double d, dist1 = 1e6, dist2 = 1e6;

CvSeqReader reader, kreader;

cvStartReadSeq( model_keypoints, &kreader, 0 );

cvStartReadSeq( model_descriptors, &reader, 0 );

for( i = 0; i < model_descriptors->total; i++ )

{

const Cv SURFPoint* kp = (const Cv SURFPoint*)kreader.ptr;

const float* mvec = (const float*)reader.ptr;

CV_NEXT_SEQ_ELEM( kreader.seq->elem_size, kreader );

CV_NEXT_SEQ_ELEM( reader.seq->elem_size, reader );

if( laplacian != kp->laplacian )

continue;

d = compare SURFDescriptors( vec, mvec, dist2, length );

if( d < dist1 )

{

dist2 = dist1;

dist1 = d;

neighbor = i;

}

else if ( d < dist2 )

dist2 = d;

}

if ( dist1 < 0.6*dist2 )

return neighbor;

return -1;

}

//用于找到两幅图像之间匹配的点对，并把匹配的点对存储在 ptpairs 向量中，其中物体(object)图像的特征点

//及其相应的描述器（局部特征）分别存储在 objectKeypoints 和 objectDescriptors，场景(image)图像的特

//征点及其相应的描述器（局部特征）分别存储在 imageKeypoints和 imageDescriptors

void findPairs( const CvSeq* objectKeypoints, const CvSeq* objectDescriptors,

const CvSeq* imageKeypoints, const CvSeq* imageDescriptors, vector<int>& ptpairs )

{

int i;

CvSeqReader reader, kreader;

cvStartReadSeq( objectKeypoints, &kreader );

cvStartReadSeq( objectDescriptors, &reader );

ptpairs.clear();

for( i = 0; i < objectDescriptors->total; i++ )

{

const Cv SURFPoint* kp = (const Cv SURFPoint*)kreader.ptr;

const float* descriptor = (const float*)reader.ptr;

CV_NEXT_SEQ_ELEM( kreader.seq->elem_size, kreader );

CV_NEXT_SEQ_ELEM( reader.seq->elem_size, reader );

int nearest_neighbor = naiveNearestNeighbor( descriptor, kp->laplacian, imageKeypoints, imageDescriptors );

if( nearest_neighbor >= 0 )

{

ptpairs.push_back(i);

ptpairs.push_back(nearest_neighbor);

}

}

}

//用于寻找物体(object)在场景(image)中的位置,位置信息保存在参数dst_corners中，参数src_corners由物

//体(object的width几height等决定，其他部分参数如上findPairs

int locatePlanarObject( const CvSeq* objectKeypoints, const CvSeq* objectDescriptors,

const CvSeq* imageKeypoints, const CvSeq* imageDescriptors,

const CvPoint src_corners[4], CvPoint dst_corners[4] )

{

double h[9];

CvMat _h = cvMat(3, 3, CV_64F, h);

vector<int> ptpairs;

vector<CvPoint2D32f> pt1, pt2;

CvMat _pt1, _pt2;

int i, n;

findPairs( objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors, ptpairs );

n = ptpairs.size()/2;

if( n < 4 )

return 0;

pt1.resize(n);

pt2.resize(n);

for( i = 0; i < n; i++ )

{

pt1[i] = ((Cv SURFPoint*)cvGetSeqElem(objectKeypoints,ptpairs[i*2]))->pt;

pt2[i] = ((Cv SURFPoint*)cvGetSeqElem(imageKeypoints,ptpairs[i*2+1]))->pt;

}

_pt1 = cvMat(1, n, CV_32FC2, &pt1[0] );

_pt2 = cvMat(1, n, CV_32FC2, &pt2[0] );

if( !cvFindHomography( &_pt1, &_pt2, &_h, CV_RANSAC, 5 ))

return 0;

for( i = 0; i < 4; i++ )

{

double x = src_corners[i].x, y = src_corners[i].y;

double Z = 1./(h[6]*x + h[7]*y + h[8]);

double X = (h[0]*x + h[1]*y + h[2])*Z;

double Y = (h[3]*x + h[4]*y + h[5])*Z;

dst_corners[i] = cvPoint(cvRound(X), cvRound(Y));

}

return 1;

}

int main(int argc, char** argv)

{

//物体(object)和场景(scene)的图像向来源

const char* object_filename = argc == 3 ? argv[1] : “box.png”;

const char* scene_filename = argc == 3 ? argv[2] : “box_in_scene.png”;

//内存存储器

CvMemStorage* storage = cvCreateMemStorage(0);

cvNamedWindow(“Object”, 1);

cvNamedWindow(“Object Correspond”, 1);

//颜色值

static CvScalar colors[] =

{

{{0,0,255}},

{{0,128,255}},

{{0,255,255}},

{{0,255,0}},

{{255,128,0}},

{{255,255,0}},

{{255,0,0}},

{{255,0,255}},

{{255,255,255}}

};

IplImage* object = cvLoadImage( object_filename, CV_LOAD_IMAGE_GRAYSCALE );

IplImage* image = cvLoadImage( scene_filename, CV_LOAD_IMAGE_GRAYSCALE );

if( !object || !image )

{

fprintf( stderr, “Can not load %s and/or %s\n”

“Usage: find_obj [<object_filename> <scene_filename>]\n”,

object_filename, scene_filename );

exit(-1);

}

IplImage* object_color = cvCreateImage(cvGetSize(object), 8, 3);

cvCvtColor( object, object_color, CV_GRAY2BGR );

//物体(object)和场景(scene)的图像的特征点

CvSeq *objectKeypoints = 0, *objectDescriptors = 0;

CvSeq *imageKeypoints = 0, *imageDescriptors = 0;

int i;

//定义Surf算法要用的参数分别为 threshold 和 extended

Cv SURFParams params = cv SURFParams(500, 1);

double tt = (double)cvGetTickCount();

//提取物体(object)和场景(scene)的图像的特征点及其描述器

cvExtract SURF( object, 0, &objectKeypoints, &objectDescriptors, storage, params );

printf(“Object Descriptors: %d\n”, objectDescriptors->total);

cvExtract SURF( image, 0, &imageKeypoints, &imageDescriptors, storage, params );

printf(“Image Descriptors: %d\n”, imageDescriptors->total);

//计算所消耗的时间

tt = (double)cvGetTickCount() – tt;

printf( “Extraction time = %gms\n”, tt/(cvGetTickFrequency()*1000.));

CvPoint src_corners[4] = {{0,0}, {object->width,0}, {object->width, object->height}, {0, object-

>height}};

//定义感兴趣的区域

CvPoint dst_corners[4];

IplImage* correspond = cvCreateImage( cvSize(image->width, object->height+image->height), 8, 1 );

//设置感兴趣区域

cvSetImageROI( correspond, cvRect( 0, 0, object->width, object->height ) );

cvCopy( object, correspond );

cvSetImageROI( correspond, cvRect( 0, object->height, correspond->width, correspond->height ) );

cvCopy( image, correspond );

cvResetImageROI( correspond );

//寻找物体(object)在场景(image)中的位置，并将信息保存

if( locatePlanarObject( objectKeypoints, objectDescriptors, imageKeypoints,

imageDescriptors, src_corners, dst_corners ))

{

for( i = 0; i < 4; i++ )

{

CvPoint r1 = dst_corners[i%4];

CvPoint r2 = dst_corners[(i+1)%4];

cvLine( correspond, cvPoint(r1.x, r1.y+object->height ),

cvPoint(r2.x, r2.y+object->height ), colors[8] );

}

}

//定义并保存物体(object)在场景(image)图形之间的匹配点对，并将其存储在向量 ptpairs 中，之后可以对

//ptpairs 进行操作

vector<int> ptpairs;

findPairs( objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors, ptpairs );

//显示匹配结果

for( i = 0; i < (int)ptpairs.size(); i += 2 )

{

Cv SURFPoint* r1 = (Cv SURFPoint*)cvGetSeqElem( objectKeypoints, ptpairs[i] );

Cv SURFPoint* r2 = (Cv SURFPoint*)cvGetSeqElem( imageKeypoints, ptpairs[i+1] );

cvLine( correspond, cvPointFrom32f(r1->pt),

cvPoint(cvRound(r2->pt.x), cvRound(r2->pt.y+object->height)), colors[8] );

}

cvShowImage( “Object Correspond”, correspond );

//显示物体(object)的所有特征点

for( i = 0; i < objectKeypoints->total; i++ )

{

Cv SURFPoint* r = (Cv SURFPoint*)cvGetSeqElem( objectKeypoints, i );

CvPoint center;

int radius;

center.x = cvRound(r->pt.x);

center.y = cvRound(r->pt.y);

radius = cvRound(r->size*1.2/9.*2);

cvCircle( object_color, center, radius, colors[0], 1, 8, 0 );

}

cvShowImage( “Object”, object_color );

cvWaitKey(0);

//释放窗口所占用的内存

cvDestroyWindow(“Object”);

cvDestroyWindow(“Object Correspond”);

return 0;

}

通过调试运行，可以得到dst_corners中的数据如下：

ptpairs 中的数据如下：

也就是：

[78]

(

29 484

77 134

82 274

206 797

228 210

243 203

244 203

249 404

295 105

347 451

360 142

417 190

427 191

436 198

445 204

452 211

466 218

473 105

486 684

502 133

521 169

522 178

527 190

530 190

532 450

533 198

535 197

539 205

542 202

544 208

547 483

558 412

559 412

583 623

586 624

587 624

594 748

595 654

597 657

)

总共有39对匹配点，第一列表示 物体(object)图像中匹配上的点，第一列表示 场景(image)图像中匹配的点，其实也就是 物体(object)图像中第28个特征点和 场景(image)图像中第484个特征点相匹配。

通过这种索引（可以这么说ptpairs中存储的是索引 ）可以求的那个特征点的坐标，如下：

//取得图像中第i个 特征点

Cv SURFPoint* r = (Cv SURFPoint*)cvGetSeqElem( objectKeypoints, i );

或

//通过ptpairs 取得图像中第ptpairs[i] 个 特征点，这个特征点是匹配上的点

Cv SURFPoint* r1 = (Cv SURFPoint*)cvGetSeqElem( objectKeypoints, ptpairs[i] );

运行示意图如下：

关于find_obj.cpp中的

#ifdef USE_FLANN

flannFindPairs( objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors, ptpairs );

#else

findPairs( objectKeypoints, objectDescriptors, imageKeypoints, imageDescriptors, ptpairs );

#endif

不外乎就是在与说明是否采用 approximate nearest-neighbor 方法来寻找匹配点对。

本文链接：http://www.yongblog.com/archives/160.html 转载请注明出处。