Which parameters (method and ransacReprojectionThreshold) from findHomography function you found to give better results in terms of a balance between accuracy and performance, and what is the reasoning?
*Edit:
I use RANSAC with ransacReprojectionThreshold = 4. But I am not sure if i can do better than this.
method of 0 assumes no outliers. The RANSAC one requires you to give a distance and this one has to be chosen with respect to your noise model/dataset: try with a few pixels (e.g. 2) and keep increasing if you are dis-satisfied by the results.
The Least-Median method uses the median of your valid points and does not assume a distance but it assumes that at least 50% of your points are valid.
Thanks for your answer, it is certainly helpful but I updated the question to mention a "balance between accuracy and performance", which is more accurate to what I had in mind.
Asked: 2012-06-26 06:38:23 -0600
Seen: 2,138 times
Last updated: Jul 08 '12
