Centralized information fusion with limited multi-view for multi-object tracking

Minti Liu; Cao Zeng; Shihua Zhao; Shidong Li

doi:10.1117/12.2626840

14 February 2022 Centralized information fusion with limited multi-view for multi-object tracking

Minti Liu, Cao Zeng, Shihua Zhao, Shidong Li

Proceedings Volume 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021); 121610U (2022) https://doi.org/10.1117/12.2626840
Event: 4th International Conference on Informatics Engineering and Information Science, 2021, Tianjin, China

Abstract

In practical radar detection applications, due to the limitation of the beam width of the pattern, limited field of view (FOV) lacks the overall perception ability of the area of interest (AOI). Especially, when unknown and time-varying targets appear in AOI, it can easily lead to missing even wrong tracking of key objects. In view of the above problems, the radar network is adopted to fuse the observation data of limited multi-view to obtain the global field of view information, and then realize the trajectories estimation of multi-object in the fusion center. Based on FInite Set STatistics (FISST) framework, mapping the newborn and death process of multiple targets within FOVs as multi- Bernoulli process, the posteriori density of multi objects is propagated recursively followed Bayesian criterion in time. The simulation results of multi-object trajectories estimation with four kinds of multi-Bernoulli (MB) filters are given under three scenarios, which illustrates that the number of interest objects and the accuracy of trajectories estimation are improved, along with the increase of the number of local observation fields of view. Furthermore, the tracking performance of labeled multi-Bernoulli (LMB) filter is superior to that of unlabeled filter.

Citation Download Citation

Minti Liu, Cao Zeng, Shihua Zhao, and Shidong Li "Centralized information fusion with limited multi-view for multi-object tracking", Proc. SPIE 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021), 121610U (14 February 2022); https://doi.org/10.1117/12.2626840

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