CODE: Coherence based decision boundaries for feature correspondence

Author

Wen-yan LIN, Singapore Management UniversityFollow
Fan WANG, Advanced Digital Sciences Centre
Ming-Ming CHENG, Nankai University
Sai-Kit YEUNG, Singapore University of Technology and Design
Philip H. S. TORR, Oxford University
Jiangbo LU, University of Illinois at Urbana-Champaign

Publication Type

Journal Article

Version

acceptedVersion

Publication Date

1-2018

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% 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.

Keywords

Feature matching, wide-baseline matching, visual correspondence, RANSAC

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volume

40

Issue

1

First Page

34

Last Page

47

ISSN

0162-8828

Identifier

10.1109/TPAMI.2017.2652468

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Citation

LIN, Wen-yan; WANG, Fan; CHENG, Ming-Ming; YEUNG, Sai-Kit; TORR, Philip H. S.; and LU, Jiangbo. CODE: Coherence based decision boundaries for feature correspondence. (2018). IEEE Transactions on Pattern Analysis and Machine Intelligence. 40, (1), 34-47.
Available at: https://ink.library.smu.edu.sg/sis_research/4800

Copyright Owner and License

Authors

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.

Additional URL

https://doi.org/10.1109/TPAMI.2017.2652468