Multi-target identity management for unknown and time-varying number of targets in clutter

Zhang, Chiyu; Kim, Dohyeung; Hwang, Inseok

doi:10.1016/j.ejcon.2021.03.006

Cited by 3 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In principle, the GM-PHD filter does not provide the trajectory of a target, so several methods have been proposed to achieve data association and track management [10,11]. Since the performance of the GM-PHD filter could be degraded (possibly significantly) in a highly cluttered environment, some studies have focussed on tracking targets in a highly cluttered environment [12,13].…”

Section: Introductionmentioning

confidence: 99%

Multiple‐model Gaussian mixture probability hypothesis density filter based on jump Markov system with state‐dependent probabilities

Sun

Kim

Hwang

2022

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

The Gaussian mixture probability density (GM‐PHD) filter has become a popular approach to solve the multiple‐target tracking (MTT) problem because it can effectively and efficiently estimate the number of targets and target states that change over time from noisy measurements. In the GM‐PHD filter, the target detection and survival probabilities, and the birth rate are assumed to be constant, irrespective of the target state. However, in some applications, for example, when the target follows the planned trajectory, the detection, survival and birth of the target depend on its state. Besides, when the target reaches a waypoint along the planned trajectory, it will take a manoeuvre to go to the next waypoint, but the GM‐PHD filter does not accommodate manoeuvring targets that switch between several motion models. To address this, we propose a multiple‐model GM‐PHD filter with state‐dependent probabilities, which can explicitly consider the mode transition probabilities, the probabilities of detection and survival, and the birth rate as a function of the target state. The performance of the proposed algorithm is demonstrated by illustrative MTT scenarios which include target manoeuvres during occlusion.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiple‐model Gaussian mixture probability hypothesis density filter based on jump Markov system with state‐dependent probabilities

Sun

Kim

Hwang

2022

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the most wide used RFS based MTT algorithms include probability hypothesis density (PHD) filter [25], Gaussian mixture PHD (GM‐PHD) filter [26], cardinality probability hypothesis density (CPHD) filter [27], and sequential Monte Carlo PHD (SMC‐PHD) filter [28]. Due to the multi‐integrals in the update step of PHD algorithm, it is hard to obtain the estimation results in time.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the stochastic process theory, the sufficient conditions for the boundedness of the state estimation error are given in a general form. Considering the target dynamic model and sensor measurement model, a lot of MTT algorithms have been proposed, such as [25–28], but few of them analyzed the stability of the algorithm. (3)Most of traditional MTT algorithms only consider the simple target dynamic model, such as [27, 28, 30 32, 34]. The designed DGMPHD algorithm is also suitable for multiple maneuvering targets, which is illustrated in the simulation section.…”

Section: Introductionmentioning

confidence: 99%

Distributed robust cooperative tracking against multiple maneuvering targets based on random finite set

Zhang

Dong

et al. 2022

IET Control Theory & Appl

View full text Add to dashboard Cite

This paper considers the distributed multi-target tracking problem with mobile sensor network. Based on the random finite set and consensus methods, a distributed multi-target tracking algorithm is designed by local filtering stage and consensus fusion stage. In the local filtering stage, the state and measurement information of multi-target are described by random finite set. Each node in the sensor network obtains the state estimates of multi-target individually by applying the probability hypothesis density filtering algorithm. To reduce the computational complexity, the Jacobian matrix and Hessian matrix are used to calculate the priori probability density. With the local neighboring interactions, the estimate results of multi-target system are obtained after the consensus fusion stage. Besides, the stochastic boundedness of the estimation error of the distributed multi-target tracking algorithm is proved by constructing a stochastic process. In the final, a simulation example is given to verify the multi-target tracking performance of the proposed algorithm.

show abstract

Gaussian mixture probability hypothesis density filter with dynamic probabilities: Application to road traffic surveillance

Sun

Hwang

2023

European Journal of Control

View full text Add to dashboard Cite

Multi-target identity management for unknown and time-varying number of targets in clutter

Cited by 3 publications

References 27 publications

Multiple‐model Gaussian mixture probability hypothesis density filter based on jump Markov system with state‐dependent probabilities

Multiple‐model Gaussian mixture probability hypothesis density filter based on jump Markov system with state‐dependent probabilities

Distributed robust cooperative tracking against multiple maneuvering targets based on random finite set

Gaussian mixture probability hypothesis density filter with dynamic probabilities: Application to road traffic surveillance

Contact Info

Product

Resources

About