Abstract
A key challenge in feature correspondence is the difficulty in differentiating true and false matches at a local descriptor level. This forces adoption of strict similarity thresholds that discard many true matches. However, if analyzed at a global level, false matches are usually randomly scattered while true matches tend to be coherent (clustered around a few dominant motions), thus creating a coherence based separability constraint. This paper proposes a non-linear regression technique that can discover such a coherence based separability constraint from highly noisy matches and embed it into a correspondence likelihood model. Once computed, the model can filter the entire set of nearest neighbor matches (which typically contains over 90 percent false matches) for true matches. We integrate our technique into a full feature correspondence system which reliably generates large numbers of good quality correspondences over wide baselines where previous techniques provide few or no matches.
Highlights
C Orrespondence between image pairs involve finding the projections of the same scene points in both images
Correspondence algorithms must accommodate a wide range of baselines and scenarios, e.g. Internet images, noisy infrared images, high resolution images, low-resolution video frames, etc
While lacking the correspondence density offered by optical flow alternatives [7], [8], [9], [10], feature matchers provide an attractive blend of wide baselines, fast speed and fine localization
Summary
C Orrespondence between image pairs involve finding the projections of the same scene points in both images. The desired stability of downstream systems requires correspondence algorithms to find as many matches as possible while keeping false matches to a minimum. Feature matching [4], [5], [6] is the correspondence solution of choice for many computer vision systems. The goal of feature matching is to correspond sparsely scattered, distinctive key-points. Feature correspondence typically discards many true matches to suppress the number of false matches [11], [12], [13]. This can cause a paucity of matches which negatively impacts downstream algorithms.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Transactions on Pattern Analysis and Machine Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.