Adaptive hill climbing and iterative closest point algorithm for multisensor image registration with partial Hausdorff distance

Xiangjie Yang; Yunlong Sheng; Weiguang Guan; Pierre Valin; Leandre Sevigny

doi:10.1117/12.381623

Translator Disclaimer

3 April 2000 Adaptive hill climbing and iterative closest point algorithm for multisensor image registration with partial Hausdorff distance

Xiangjie Yang, Yunlong Sheng, Weiguang Guan, Pierre Valin, Leandre Sevigny

Author Affiliations +

Proceedings Volume 4051, Sensor Fusion: Architectures, Algorithms, and Applications IV; (2000) https://doi.org/10.1117/12.381623
Event: AeroSense 2000, 2000, Orlando, FL, United States

Abstract

Challenge in the registration of battlefield images in visible and far-infrared bands is the feature inconsistency. We propose a contour-based approach for the registration and apply two free-form curve-matching algorithms: adaptive hill climbing and the iterative closest point algorithm. Both algorithms do not require explicit curve feature correspondence, are designed to be robust against outliers. We formulate the search as an adaptive hill climbing optimization for minimizing the partial Hausdorff distances. In the iterative closest point algorithm we choose the mean partial distance as the objective function, so that outliers can be easily handled by using rank order statistics.

Citation Download Citation

Xiangjie Yang, Yunlong Sheng, Weiguang Guan, Pierre Valin, and Leandre Sevigny "Adaptive hill climbing and iterative closest point algorithm for multisensor image registration with partial Hausdorff distance", Proc. SPIE 4051, Sensor Fusion: Architectures, Algorithms, and Applications IV, (3 April 2000); https://doi.org/10.1117/12.381623

ACCESS THE FULL ARTICLE