Re: Image alignment and feature extraction
b) What the difference between FAST, oFAST and rBRIEF and STAR (and FREAK?) is and which one likely to be the most appropriate for random
Hey Ankit, Thanks for your response, it's very helpful. pictures of the Sun?
Currently, I cannot answer this question in complete confidence, partly
because I am yet to complete and test FREAK and partly because I am not aware of the data, or the kind of solar images that are going to be aligned. Can you give some examples of pairs of images that are required to be aligned in Solar Physics. Some queries that one would have about the data are like : Are the solar images that need to be aligned generated from the same camera but at different time intervals? Generally yes. Sometimes one series of images taken with the same camera at different times is aligned, primarily to compensate for small variation in telescope pointing, and then that is used for other images which are assumed to have the same pointing.
Is the scaling or the zoom factor changing?
This would be unlikely.
Is it only the Sun's rotation about its axis that is generating these two different images or some other factor is also involved?
Generally solar rotation is compensated for by using models of the rotation rather than image registration.
Currently, ORB is the best bet, because of its speed and invariance to both scaling and rotation.
Shiny.
c) What else needs to be done to turn this feature detection and
description work into registration?
Image Registration Pipeline can be summarized as : Detect
features(keypoints) --> Compute Descriptors --> Match keypoints --> Treat one image as the reference and Estimate the Geometric Transformation required to get the second image using the matches. ORB does the first three and the 4th stage is what needs to be done. These slides[3] explain it better. So the RANSAC algorithm from those slides? Thanks again. Stuart
participants (1)
-
Stuart Mumford