Novel Approach for Nonlinear Maneuvering Target Tracking Based on Input Estimation

2011 ◽  
Vol 110-116 ◽  
pp. 4415-4423 ◽  
Author(s):  
Hodjat Rahmati ◽  
Hamid Khaloozadeh ◽  
Moosa Ayati

In this paper, a new method for maneuvering target tracking (MTT) based on nonlinear input estimation (IE) is innovated and is employed for tracking of maneuvering targets. Proposed method augments the states and unknown inputs (maneuvers) in a higher order state space realization and estimates both of them simultaneously. The concurrent estimation of states and inputs eliminates the maneuver detection delay which is popular in the conventional IE methods. The proposed method has excellent performance for both maneuvering and non-maneuvering stages. Also, a model with highly nonlinear dynamics for maneuvering targets is given and is used in the numerical simulations to analyze the performance of the proposed maneuvering target tracking method. Furthermore the proposed method is compared with a conventional IE method and the simulation results show the effectiveness of the proposed method.

2014 ◽  
Vol 989-994 ◽  
pp. 2212-2215
Author(s):  
Song Gao ◽  
Chao Bo Chen ◽  
Qian Gong

As for the problem of maneuvering target tracking in the clutter environment, this paper combines IMM with PHD and realizes it through approach of particle filter. This algorithm avoids the troublesome problem of data association, and takes advantage of probability hypothesis density (PHD) filter in tracking maneuvering targets and interacting multi-model (IMM) algorithm in the field of model switching effectively, in the clutter environment, the status of the targets can be estimated precisely and steadily. This paper compares the proposed filtering algorithm with the classical IMM algorithm in performance, and the simulation results show that, the improved filtering algorithm has good tracking performance and tracking accuracy.


2011 ◽  
Vol 383-390 ◽  
pp. 5609-5614
Author(s):  
Ye Tian ◽  
Hong Jiang ◽  
Quan Xin Ding ◽  
Guo Wei Liang

A turn rate estimation based adaptive interactive multiple model algorithm is put forward to solve model-set mismatch problem of target tracking algorithm applying to high maneuvering target. By considering both the estimation and the estimated variance of target’s turn rate, model-set is selected according to a rule based on the coefficient of variance of turn rate estimation. When turn rate estimation is acceptable, model-set is constructed according to turn rate estimation to reduce competition among models. When turn rate estimation is unacceptable, standard IMM algorithm model-set is applied to increase coverage of model-set. Simulation shows this algorithm improves tracking performance especially for high maneuvering targets.


2002 ◽  
Author(s):  
Jianxun Li ◽  
Zhongliang Jing ◽  
Feng Li

Multiple maneuvering target tracking in a dense clutter environment is investigated. An effective parallel processing algorithm based on state fusion and fast joint probabilistic data association (FJPDA) is proposed. State fusion and feedback of all state information are used to fit different movements of targets. The FJPDA combining cluster matrix decomposition with fast data association algorithm is built for tracking multiple targets. Two examples are simulated to prove the validity and reliability of the proposed new algorithm.


Sign in / Sign up

Export Citation Format

Share Document