Autonomous Motion Conference Paper 2016

Parameter Learning for Improving Binary Descriptor Matching

Oxfordlight

Binary descriptors allow fast detection and matching algorithms in computer vision problems. Though binary descriptors can be computed at almost two orders of magnitude faster than traditional gradient based descriptors, they suffer from poor matching accuracy in challenging conditions. In this paper we propose three improvements for binary descriptors in their computation and matching that enhance their performance in comparison to traditional binary and non-binary descriptors without compromising their speed. This is achieved by learning some weights and threshold parameters that allow customized matching under some variations such as lighting and viewpoint. Our suggested improvements can be easily applied to any binary descriptor. We demonstrate our approach on the ORB (Oriented FAST and Rotated BRIEF) descriptor and compare its performance with the traditional ORB and SIFT descriptors on a wide variety of datasets. In all instances, our enhancements outperform standard ORB and is comparable to SIFT.

Author(s): Bharath Sankaran and Srikumar Ramalingam and Yuichi Taguchi
Book Title: International Conference on Intelligent Robots and Systems (IROS) 2016
Year: 2016
Month: October
Bibtex Type: Conference Paper (inproceedings)
Event Name: IEEE/RSJ International Conference on Intelligent Robots and Systems 2016
Event Place: Daejeon, Korea
State: Published
Electronic Archiving: grant_archive
Attachments:

BibTex

@inproceedings{sankaran_iros_2016,
  title = {Parameter Learning for Improving Binary Descriptor Matching},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS) 2016},
  abstract = {Binary descriptors allow fast detection and matching algorithms in computer vision problems. Though binary descriptors can be computed at almost two orders of magnitude faster than traditional gradient based descriptors, they suffer from poor matching accuracy in challenging conditions. In this paper we propose three improvements for binary descriptors in their computation and matching that enhance their performance in comparison to traditional binary and non-binary descriptors without compromising their speed. This is achieved by learning some weights and threshold parameters that allow customized matching under some variations such as lighting and viewpoint. Our suggested improvements can be easily applied to any binary descriptor. We demonstrate our approach on the ORB (Oriented FAST and Rotated BRIEF) descriptor and compare its performance with the traditional ORB and SIFT descriptors on a wide variety of datasets. In all instances, our enhancements outperform standard ORB and is comparable to SIFT.},
  month = oct,
  year = {2016},
  slug = {sankaran_iros_2016},
  author = {Sankaran, Bharath and Ramalingam, Srikumar and Taguchi, Yuichi},
  month_numeric = {10}
}