1 November 2016 Learning to assign binary weights to binary descriptor
Author Affiliations +
Proceedings Volume 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control; 1015721 (2016) https://doi.org/10.1117/12.2246737
Event: International Symposium on Optoelectronic Technology and Application 2016, 2016, Beijing, China
Constructing robust binary local feature descriptors are receiving increasing interest due to their binary nature, which can enable fast processing while requiring significantly less memory than their floating-point competitors. To bridge the performance gap between the binary and floating-point descriptors without increasing the computational cost of computing and matching, optimal binary weights are learning to assign to binary descriptor for considering each bit might contribute differently to the distinctiveness and robustness. Technically, a large-scale regularized optimization method is applied to learn float weights for each bit of the binary descriptor. Furthermore, binary approximation for the float weights is performed by utilizing an efficient alternatively greedy strategy, which can significantly improve the discriminative power while preserve fast matching advantage. Extensive experimental results on two challenging datasets (Brown dataset and Oxford dataset) demonstrate the effectiveness and efficiency of the proposed method.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhoudi Huang, Zhoudi Huang, Zhenzhong Wei, Zhenzhong Wei, Guangjun Zhang, Guangjun Zhang, } "Learning to assign binary weights to binary descriptor", Proc. SPIE 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control, 1015721 (1 November 2016); doi: 10.1117/12.2246737; https://doi.org/10.1117/12.2246737

Back to Top