OpenCV Q&A Forum - RSS feedhttp://answers.opencv.org/questions/OpenCV answersenCopyright <a href="http://www.opencv.org">OpenCV foundation</a>, 2012-2018.Fri, 14 Feb 2020 10:41:49 -0600Refining perspective transformation in epipolar geometryhttp://answers.opencv.org/question/7689/refining-perspective-transformation-in-epipolar-geometry/Given two epipolar pics of the same scene from (slightly) different angles, and given corresponding points in the two pics that were manually curated (golden truth), one can calculate the perspective transformation matrix between the two camera planes.
However, when applying this transformation on a new point in one of the images to calculate the location of the corresponding coordinates of the point in the other image, often time the calculated coordinates hae a (small) offset from the real location (resulting from noise, approximation, etc).
What can be done to improve the accuracy of the location of the calculated point? What is the state of the art in this regard? Are there any post-refinements based on local descriptors and local search that could help improve the accuracy of the location?Tue, 19 Feb 2013 10:22:51 -0600http://answers.opencv.org/question/7689/refining-perspective-transformation-in-epipolar-geometry/Answer by wisewolf76 for <p>Given two epipolar pics of the same scene from (slightly) different angles, and given corresponding points in the two pics that were manually curated (golden truth), one can calculate the perspective transformation matrix between the two camera planes.</p>
<p>However, when applying this transformation on a new point in one of the images to calculate the location of the corresponding coordinates of the point in the other image, often time the calculated coordinates hae a (small) offset from the real location (resulting from noise, approximation, etc).</p>
<p>What can be done to improve the accuracy of the location of the calculated point? What is the state of the art in this regard? Are there any post-refinements based on local descriptors and local search that could help improve the accuracy of the location?</p>
http://answers.opencv.org/question/7689/refining-perspective-transformation-in-epipolar-geometry/?answer=226283#post-id-226283When you compute the homography using correspondences between two images, you are computing the real transformation between points if only if they all lie on the same plane or if the camera moved with perfect rotation. Otherwise the homography is just an approximation. The only way to map all the points in a pefect way is computing a dense 3D map between the two views using stereopsis.Fri, 14 Feb 2020 10:41:49 -0600http://answers.opencv.org/question/7689/refining-perspective-transformation-in-epipolar-geometry/?answer=226283#post-id-226283