9 August 2018 Video tracking technology based on improved compressed sensing algorithm
Author Affiliations +
Proceedings Volume 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018); 1080641 (2018) https://doi.org/10.1117/12.2502822
Event: Tenth International Conference on Digital Image Processing (ICDIP 2018), 2018, Shanghai, China
Abstract
The video tracking technology is applied widely in military field, intelligent monitoring, security and human-computer interaction fields. In the paper, the neighborhood and dimension of the descriptor of SIFT (Scale Invariant Feature Transform, SIFT) is discussed, then a novel updating strategy of the learning rate of the classifier in the compressive theory is proposed. Target drifting phenomena and occlusion are handled properly after combined with efficient SIFT feature descriptor and improved compressed sensing algorithm. The experiments show that this method not only can improve the real-time performance of tracking target, but also can carry on the tracking of moving target accurately in the event of a target drifting and occlusion.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhemin Zhuang, Naihai Lei, and Alex Noel Josephraj "Video tracking technology based on improved compressed sensing algorithm", Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 1080641 (9 August 2018); doi: 10.1117/12.2502822; https://doi.org/10.1117/12.2502822
PROCEEDINGS
5 PAGES


SHARE
Advertisement
Advertisement
Back to Top