3

我从sourceImage中提取了四个角:

src_vertices[0] = corners[upperLeft];
src_vertices[1] = corners[upperRight];   
src_vertices[2] = corners[downLeft];
src_vertices[3] = corners[downRight];

这四个角像这样扭曲到destinationImage

dst_vertices[0] = Point(0,0);
dst_vertices[1] = Point(width, 0); 
dst_vertices[2] = Point(0, height);
dst_vertices[3] = Point(width, height);

Mat warpPerspectiveMatrix = getPerspectiveTransform(src_vertices, dst_vertices);
cv::Size size_d =  Size(width, height);
cv::Mat DestinationImage(width,height,CV_8UC3);
warpPerspective(sourceImage, destinationImage, warpPerspectiveMatrix, size_d, INTER_LINEAR, BORDER_CONSTANT);

现在我的问题是:

我有一个取自destinationImage的点p(x,y)如何在原始sourceImage 中检索该点的坐标

换句话说,我想使用 warpPerspectiveMatrix 来做 getPerspectiveTransform 的相反工作

4

1 回答 1

6

你想要逆透视变换。如果您的原始变换是 S->S',则需要变换矩阵 S'->S

Mat InversewarpPerspectiveMatrix = getPerspectiveTransform(dst_vertices, src_vertices);

然后你制作一个稀疏矩阵

Mat PerspectiveCoordinates containing the vector x,y.

最后你想打电话

PerspectiveTransform(PerspectiveCoordinates,OriginalCoordinates,InversewarpPerspectiveMatrix)
于 2013-01-15T20:20:45.143 回答