计算关键点的新阵地 [英] Calculating new positions of keypoints

问题描述

能有人帮助我，我们怎么能计算转换图像中关键点的新阵地，是在原始图像检测到的关键点。我使用OpenCV的同形矩阵和warpPerspective使转换后的图片。

can somebody help me, how we can calculate the new positions of keypoints in the transformed image,the keypoints were detected in original image. I am using opencv homography matrix and warpPerspective to make the transformed image.

下面是一个code ..

Here is a code..

...
 std::vector< Point2f > points1,points2;
 for( int i = 0; i < matches1.size(); i++ )
    {
     points1.push_back( keypoints_input1[matches1[i].queryIdx ].pt );
     points2.push_back( keypoints_input2[matches1[i].trainIdx ].pt );
    }
 /* Find the Homography Matrix for current and next frame*/
 Mat H1 = findHomography( points2, points1, CV_RANSAC );
 /* Use the Homography Matrix to warp the images*/
cv::Mat result1;
warpPerspective(input2, result1, H1, Size(input2.cols+150, input2.rows+150),              
INTER_CUBIC);
...
}

现在我要计算的RESULT1图像中points2的新位置。

Now I want to calculate the new positions of points2 in the result1 image.

例如下面的变换的图像中，我们知道的角点。现在我要计算的关键点的新位置改造前说{（X1，Y1），（X2，Y2），（X3，Y3）...}，我们该如何计算呢？

For example in the below transformed image , we know the corner points. Now I want to calculate the new position of the keypoints say before transformation {(x1,y1),(x2,y2),(x3,y3)...}, How we can calculate it?

更新：OpenCV的perspectiveTransform做什么，我试图做的。

Update: opencv 'perspectiveTransform' does what I trying to do.

推荐答案

让我们叫 I 通过扭曲图像获得的图像 I 使用单应 ^ h 。

Let's call I' the image obtained by warping image I using homography H.

如果您提取关键点的 M _I =（X _I ，Y <子> I ，1）原始图像 I ，就可以得到关键点的 M' _I 在扭曲的图像我'使用单应变换：S * M' _I = H *的 M _I 。注意比例因子S，如果你想在关键点在像素坐标，你的有无的扩展 M' _I 这样的第三个因素是1

If you extracted keypoints m_i = (x_i, y_i, 1) in original image I, you can get the keypoints m'_i in the warped image I' using the homography transform: S * m'_i = H * m_i. Notice the scale factor S, if you want the keypoints coordinates in pixels, you have to scale m'_i so that the third element is 1.

如果你想了解其中规模因素来自，看看齐次坐标

If you want to understand where the scale factor comes from, have a look at Homogeneous Coordinates.

此外，还有一个OpenCV的功能，这种转变适用于点的数组： perspectiveTransform （文档）。

Also, there is an OpenCV function to apply this transformation to an array of points: perspectiveTransform(documentation).

这篇关于计算关键点的新阵地的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！