Occlusion processing using particle filter and background subtraction algorithms

Tongqing Guo; Jian Rong; Kui Lu; Xiaochun Zhong

doi:10.1117/12.2019700

19 March 2013 Occlusion processing using particle filter and background subtraction algorithms

Tongqing Guo, Jian Rong, Kui Lu, Xiaochun Zhong

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.

Citation Download Citation

Tongqing Guo, Jian Rong, Kui Lu, and 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); https://doi.org/10.1117/12.2019700

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available