Distributed interacted multisensor joint probabilistic data association algorithm based on D-S theory |
| |
摘 要: | With the development of science and technique, the surveillance systems used in the battlefield have been developed into multisensor systems. Therefore, the multisenor multitarget tracking algorithms, such as centralized multisensor joint probabilistic da…
|
收稿时间: | 20 June 2005 |
修稿时间: | 8 December 2005 |
Distributed interacted multisensor joint probabilistic data association algorithm based on D-S theory |
| |
Authors: | ZHANG Jingwei XIU Jianjuan HE You XIONG Wei |
| |
Affiliation: | Research Institute of Information Fusion, Naval Aeronautical Engineering Institute, Yantai 264001, China |
| |
Abstract: | In order to resolve the multisensor multiplied maneuvering target tracking problem, this paper presents a distributed interacted multiple model multisensor joint probabilistic data association algorithm (DIMM-MSJPDA). First of all, the interacted multiple model joint probabilistic data association algorithm is applied to each sensor, and then the state estimation, estimation covariance, model probability, combined innovation, innovation covariance are delivered to the fusion center. Then, the tracks from each sensor are correlated and the D-S evidence theory is used to gain the model probability of an identical target. Finally, the ultimate state estimation of each target is calculated according to the new model probability, and the state estimation is transmitted to each sensor. Simulations are designed to test the tracking performance of DIMM-MSJPDA algorithm. The results show that the use of DIMM-MSJPDA algorithm enables the distributed multisensor system to track multiplied maneuvering targets and its tracking performance is much better than that of IMMJPDA algorithm. |
| |
Keywords: | distributed interacted multisensor data association |
本文献已被 万方数据 SpringerLink 等数据库收录! |
|