【OpenCV】透视变换 Perspective Transformation（续）

透视变换的原理和矩阵求解请参见前一篇《透视变换 Perspective Transformation》。在OpenCV中也实现了透视变换的公式求解和变换函数。

求解变换公式的函数：

[cpp] view plain copy

Mat getPerspectiveTransform(const Point2f src[], const Point2f dst[])

输入原始图像和变换之后的图像的对应4个点，便可以得到变换矩阵。之后用求解得到的矩阵输入perspectiveTransform便可以对一组点进行变换：

[cpp] view plain copy

void perspectiveTransform(InputArray src, OutputArray dst, InputArray m)

注意这里src和dst的输入并不是图像，而是图像对应的坐标。应用前一篇的例子，做个相反的变换：

[cpp] view plain copy

int main( )
{
Mat img=imread("boy.png");
int img_height = img.rows;
int img_width = img.cols;
vector<Point2f> corners(4);
corners[0] = Point2f(0,0);
corners[1] = Point2f(img_width-1,0);
corners[2] = Point2f(0,img_height-1);
corners[3] = Point2f(img_width-1,img_height-1);
vector<Point2f> corners_trans(4);
corners_trans[0] = Point2f(150,250);
corners_trans[1] = Point2f(771,0);
corners_trans[2] = Point2f(0,img_height-1);
corners_trans[3] = Point2f(650,img_height-1);
Mat transform = getPerspectiveTransform(corners,corners_trans);
cout<<transform<<endl;
vector<Point2f> ponits, points_trans;
for(int i=0;i<img_height;i++){
for(int j=0;j<img_width;j++){
ponits.push_back(Point2f(j,i));
}
}
perspectiveTransform( ponits, points_trans, transform);
Mat img_trans = Mat::zeros(img_height,img_width,CV_8UC3);
int count = 0;
for(int i=0;i<img_height;i++){
uchar* p = img.ptr<uchar>(i);
for(int j=0;j<img_width;j++){
int y = points_trans[count].y;
int x = points_trans[count].x;
uchar* t = img_trans.ptr<uchar>(y);
t[x*3] = p[j*3];
t[x*3+1] = p[j*3+1];
t[x*3+2] = p[j*3+2];
count++;
}
}
imwrite("boy_trans.png",img_trans);
return 0;
}

得到变换之后的图片：

注意这种将原图变换到对应图像上的方式会有一些没有被填充的点，也就是右图中黑色的小点。解决这种问题一是用差值的方式，再一种比较简单就是不用原图的点变换后对应找新图的坐标，而是直接在新图上找反向变换原图的点。说起来有点绕口，具体见前一篇《透视变换 Perspective Transformation》的代码应该就能懂啦。

除了getPerspectiveTransform()函数，OpenCV还提供了findHomography()的函数，不是用点来找，而是直接用透视平面来找变换公式。这个函数在特征匹配的经典例子中有用到，也非常直观：

[cpp] view plain copy

int main( int argc, char** argv )
{
Mat img_object = imread( argv[1], IMREAD_GRAYSCALE );
Mat img_scene = imread( argv[2], IMREAD_GRAYSCALE );
if( !img_object.data || !img_scene.data )
{ std::cout<< " --(!) Error reading images " << std::endl; return -1; }
//-- Step 1: Detect the keypoints using SURF Detector
int minHessian = 400;
SurfFeatureDetector detector( minHessian );
std::vector<KeyPoint> keypoints_object, keypoints_scene;
detector.detect( img_object, keypoints_object );
detector.detect( img_scene, keypoints_scene );
//-- Step 2: Calculate descriptors (feature vectors)
SurfDescriptorExtractor extractor;
Mat descriptors_object, descriptors_scene;
extractor.compute( img_object, keypoints_object, descriptors_object );
extractor.compute( img_scene, keypoints_scene, descriptors_scene );
//-- Step 3: Matching descriptor vectors using FLANN matcher
FlannBasedMatcher matcher;
std::vector< DMatch > matches;
matcher.match( descriptors_object, descriptors_scene, matches );
double max_dist = 0; double min_dist = 100;
//-- Quick calculation of max and min distances between keypoints
for( int i = 0; i < descriptors_object.rows; i++ )
{ double dist = matches[i].distance;
if( dist < min_dist ) min_dist = dist;
if( dist > max_dist ) max_dist = dist;
}
printf("-- Max dist : %f \n", max_dist );
printf("-- Min dist : %f \n", min_dist );
//-- Draw only "good" matches (i.e. whose distance is less than 3*min_dist )
std::vector< DMatch > good_matches;
for( int i = 0; i < descriptors_object.rows; i++ )
{ if( matches[i].distance < 3*min_dist )
{ good_matches.push_back( matches[i]); }
}
Mat img_matches;
drawMatches( img_object, keypoints_object, img_scene, keypoints_scene,
good_matches, img_matches, Scalar::all(-1), Scalar::all(-1),
vector<char>(), DrawMatchesFlags::NOT_DRAW_SINGLE_POINTS );
//-- Localize the object from img_1 in img_2
std::vector<Point2f> obj;
std::vector<Point2f> scene;
for( size_t i = 0; i < good_matches.size(); i++ )
{
//-- Get the keypoints from the good matches
obj.push_back( keypoints_object[ good_matches[i].queryIdx ].pt );
scene.push_back( keypoints_scene[ good_matches[i].trainIdx ].pt );
}
Mat H = findHomography( obj, scene, RANSAC );
//-- Get the corners from the image_1 ( the object to be "detected" )
std::vector<Point2f> obj_corners(4);
obj_corners[0] = Point(0,0); obj_corners[1] = Point( img_object.cols, 0 );
obj_corners[2] = Point( img_object.cols, img_object.rows ); obj_corners[3] = Point( 0, img_object.rows );
std::vector<Point2f> scene_corners(4);
perspectiveTransform( obj_corners, scene_corners, H);
//-- Draw lines between the corners (the mapped object in the scene - image_2 )
Point2f offset( (float)img_object.cols, 0);
line( img_matches, scene_corners[0] + offset, scene_corners[1] + offset, Scalar(0, 255, 0), 4 );
line( img_matches, scene_corners[1] + offset, scene_corners[2] + offset, Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[2] + offset, scene_corners[3] + offset, Scalar( 0, 255, 0), 4 );
line( img_matches, scene_corners[3] + offset, scene_corners[0] + offset, Scalar( 0, 255, 0), 4 );
//-- Show detected matches
imshow( "Good Matches & Object detection", img_matches );
waitKey(0);
return 0;
}

代码运行效果：

findHomography()函数直接通过两个平面上相匹配的特征点求出变换公式，之后代码又对原图的四个边缘点进行变换，在右图上画出对应的矩形。这个图也很好地解释了所谓透视变换的“Viewing Plane”。

（转载请注明作者和出处：http://blog.csdn.net/xiaowei_cqu 未经允许请勿用于商业用途）

from: http://blog.csdn.net/xiaowei_cqu/article/details/26478135

【OpenCV】透视变换 Perspective Transformation（续）相关推荐

【OpenCV】透视变换 Perspective Transformation
透视变换的原理和矩阵求解请参见前一篇<透视变换 Perspective Transformation>.在OpenCV中也实现了透视变换的公式求解和变换函数. 求解变换公式的函数: Mat ...
【图像处理】透视变换 Perspective Transformation
透视变换(Perspective Transformation)是将图片投影到一个新的视平面(Viewing Plane),也称作投影映射(Projective Mapping).通用的变换公式为: ...
【CG】透视变换(Perspective Transformation)
起源透视与消失点单点透视 - 1 个消失点两点透视 - 2个消失点三点透视 - 3个消失点透视投影变换透视变换矩阵透视变换矩阵与 Homography.相机内参的关系透视与车载环境的联 ...
【图像处理】透视变换 Perspective Transformation(含续加部分)
本文博文地址:https://blog.csdn.net/xiaowei_cqu/article/details/26471527#commentsedit 续文博文地址:https://blog.c ...
【图像处理】透视变换 Perspective Transformation（小细节修正和推导流程补充）
这部分的推导,首先是求解∆x3,∆y3,然后通过得到的方程组,求解可得a13,a23,然后通过∆x1,∆x2分别求得a21,a11,同样的通过∆y1,∆y2求得a22和a12,至此透视变换矩阵所有元素 ...
透视变换（perspective transformation）
透视变换(Perspective Transformation)是将图片投影到一个新的视平面(Viewing Plane),也称作投影映射(Projective Mapping).如下图所示透视变换 ...
详解 OpenCV 透视变换原理及实例
OpenCV提供了两种图片变换的方式:仿射变换和透视变换,两者的区别很容易区分, 前者是将矩形的图片变成平行四边形后者是将图片变成梯形这两种变换虽然都有各自的应用场景,但在实际的图片变换中由于透视 ...
Opencv透视变换——cv::getPerspectiveTransform()与cv::warpPerspective()详解
透视变换(Perspective Transformation)是将成像投影到一个新的视平面(Viewing Plane),也称作投影映射(Projective Mapping).如图1,通过透视变换 ...
图像处理中的投影变换（Perspective Transformation）
透视变换(Perspective Transformation)是将图片投影到一个新的视平面(Viewing Plane),也称作投影映射(Projective Mapping).通用的变换公式为: ...

【OpenCV】透视变换 Perspective Transformation（续）

（转载请注明作者和出处：http://blog.csdn.net/xiaowei_cqu 未经允许请勿用于商业用途）

【OpenCV】透视变换 Perspective Transformation（续）相关推荐

最新文章

热门文章