Abstract

To address feature matching problem where there is only partial overlap between the two feature sets, minimisation of an energy function consisting of feature matching costs and a concave regularisation term capable of handling partial overlaps is proposed. To improve robustness to disturbances, a path following strategy for minimisation which dynamically combines weights of the two terms is adopted. Experimental results verify better performance of the method over several state-of-the-art methods.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call