19 March 2013 Occlusion processing using particle filter and background subtraction algorithms
Author Affiliations +
Proceedings Volume 8762, PIAGENG 2013: Intelligent Information, Control, and Communication Technology for Agricultural Engineering; 87621U (2013) https://doi.org/10.1117/12.2019700
Event: Third International Conference on Photonics and Image in Agriculture Engineering (PIAGENG 2013), 2013, Sanya, China
Abstract
We present an algorithm based on the Particle Filter algorithmand Background Subtraction algorithm. Particle Filter can track target robustly under kinds of noise conditions, and it’s robust to partial occlusion.However, it cannot recover from large proportion of occlusion and total occlusion.Background Subtraction algorithmcan detectnew target which emergeon a relatively stable background.The hybrid algorithm can recover fromlarge proportion of occlusion and total occlusion. A new occlusion measurement factor is imported to switchthe Particle Filter algorithm to Background subtraction algorithm when the target is occluded largely or totally, and switch Background subtraction algorithm to the Particle Filter algorithm when the target went out of the occlusion. The experimental results show that the hybrid algorithm was robust to partial and total occlusions.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tongqing Guo, Tongqing Guo, Jian Rong, Jian Rong, Kui Lu, Kui Lu, Xiaochun Zhong, Xiaochun Zhong, } "Occlusion processing using particle filter and background subtraction algorithms", Proc. SPIE 8762, PIAGENG 2013: Intelligent Information, Control, and Communication Technology for Agricultural Engineering, 87621U (19 March 2013); doi: 10.1117/12.2019700; https://doi.org/10.1117/12.2019700
PROCEEDINGS
5 PAGES


SHARE
Back to Top