How can I retrieve the points of the homography computed findHomography and RANSAC?

c++ opencv ransac
Tongxin Wang picture Tongxin Wang · Jul 23, 2015 · Viewed 7.5k times · Source

I am new to OpenCV. I noticed that the line

Mat H = findHomography( obj, scene, CV_RANSAC );

helps to find the homography H using RANSAC.

However, I need the locations of the 'purified' matching points after RANSAC and I simply cannot find which function I can use. I need a function that uses RANSAC and returns the matching points' locations after RANSAC.

Answer

Miki picture Miki · Jul 29, 2015

findHomography can optionally provide the mask of inliers and outliers (inliers are what you call purified matching).

C++: Mat findHomography(InputArray srcPoints, InputArray dstPoints, int method=0, double ransacReprojThreshold=3, OutputArray mask=noArray() )

Python: cv2.findHomography(srcPoints, dstPoints[, method[, ransacReprojThreshold[, mask]]]) → retval, mask

You can use only inliers (i.e. points with corresponding mask value equals to 1) when doing your match.

Related questions

Using estimateRigidTransform instead of findHomography

The example in the link below is using findHomography to get the transformation between two sets of points. I want to limit the degrees of freedom used in the transformation so want to replace findHomography with estimateRigidTransform. http://docs.opencv.…

Read More
RANSAC-like implementation for arbitrary 2D sets

TL;DR : Is there a C++ implementation of RANSAC or other robust correspondence algorithms that is freely usable with arbitrary 2D point sets? I know that many implementations exist that include or make use of correspondence algorithms such as RANSAC (…

Read More
OpenCV C++ - findHomography values meaning

I've already check on stackOverflaw and especially in this link but it didn't answer to my question. I compute an homography using Ransac with OpenCv in order to match two pictures. Here the code corresponding : Mat H = findHomography( obj, scene, …

Read More