Research on anti-occlusion and anti-deformation tracking based on background prediction and progressive detection

Zili Tang; Yuanyuan Zhou; Bo Zhang; Tiejun Zhou; Zhizheng Zhang; Haiying Wu

doi:10.1117/12.2586401

12 March 2021 Research on anti-occlusion and anti-deformation tracking based on background prediction and progressive detection

Zili Tang, Yuanyuan Zhou, Bo Zhang, Tiejun Zhou, Zhizheng Zhang, Haiying Wu

Author Affiliations +

Proceedings Volume 11763, Seventh Symposium on Novel Photoelectronic Detection Technology and Applications; 117632M (2021) https://doi.org/10.1117/12.2586401
Event: Seventh Symposium on Novel Photoelectronic Detection Technology and Application 2020, 2020, Kunming, China

Abstract

In view of the problems of occlusion and deformation identification and stable tracking, especially the problems of occlusion detection, template update strategy and recapture after long term occlusion under complex background, an engineering implementation of anti-occlusion and anti-deformation tracking method is proposed. And an improved kernel correlation filter based on background prediction and multi-level progressive detection is designed. The algorithm completes the detection and recognition of occlusion and deformation. The method effectively improves the detection efficiency and tracking reliability when the target is occluded and deformed in the complex underground.

Citation Download Citation

Zili Tang, Yuanyuan Zhou, Bo Zhang, Tiejun Zhou, Zhizheng Zhang, and Haiying Wu "Research on anti-occlusion and anti-deformation tracking based on background prediction and progressive detection", Proc. SPIE 11763, Seventh Symposium on Novel Photoelectronic Detection Technology and Applications, 117632M (12 March 2021); https://doi.org/10.1117/12.2586401

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