2 March 2016 A point matching algorithm based on reference point pair
Author Affiliations +
Proceedings Volume 9901, 2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015); 990104 (2016) https://doi.org/10.1117/12.2234832
Event: 2015 ISPRS International Conference on Computer Vision in Remote Sensing, 2015, Xiamen, China
Abstract
Outliers and occlusions are important degradation in the real application of point matching. In this paper, a novel point matching algorithm based on the reference point pairs is proposed. In each iteration, it firstly eliminates the dubious matches to obtain the relatively accurate matching points (reference point pairs), and then calculates the shape contexts of the removed points with reference to them. After re-matching the removed points, the reference point pairs are combined to achieve better correspondences. Experiments on synthetic data validate the advantages of our method in comparison with some classical methods.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Huanxin Zou, Huanxin Zou, Youqing Zhu, Youqing Zhu, Shilin Zhou, Shilin Zhou, Lin Lei, Lin Lei, } "A point matching algorithm based on reference point pair", Proc. SPIE 9901, 2nd ISPRS International Conference on Computer Vision in Remote Sensing (CVRS 2015), 990104 (2 March 2016); doi: 10.1117/12.2234832; https://doi.org/10.1117/12.2234832
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Determining the Pose of an Object
Proceedings of SPIE (June 09 1986)
Constructing long edge segments for object recognition
Proceedings of SPIE (August 01 1992)
Recognition of 3-D Scene with Partially Occluded Objects
Proceedings of SPIE (March 27 1987)
Generalizing recognition strategies
Proceedings of SPIE (April 13 1993)
Multiscale stochastic approach to object detection
Proceedings of SPIE (October 22 1993)
Efficient Encoding Of Local Shape Features For 3 D...
Proceedings of SPIE (March 27 1989)

Back to Top