Robust multi-sensor generalized labeled multi-Bernoulli filter

Do, Cong-Thanh; Nguyen, Tran Thien Dat; Nguyen, Ha Q.

doi:10.1016/j.sigpro.2021.108368

Cited by 14 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mismatches between the assumed model and the reality may result in performance degradation of the filter, such as erroneous state and cardinality estimations [18]. Several versions of RFS filters, including CPHD [5] and GLMB [19,20] filter, have been proposed to adaptively estimate unknown detection profile and clutter rate while filtering. However, these methods are less effective when the detection profile and clutter background evolve rapidly compared to the measurement-update rate.…”

Section: Possibility Generalizedmentioning

confidence: 99%

See 1 more Smart Citation

Possibility Generalized Labeled Multi-Bernoulli Filter for Multi-Target Tracking Under Epistemic Uncertainty

Cai

Houssineau

Jones

et al. 2022

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

This paper presents a flexible modeling framework for multi-target tracking based on the theory of Outer Probability Measures (OPMs). The notion of labeled uncertain finite set is introduced and utilized as the basis to derive a possibilistic analog of the δ-Generalized Labeled Multi-Bernoulli (δ-GLMB) filter, in which the uncertainty in the multi-target system is represented by possibility functions instead of probability distributions. The proposed method inherits the capability of the standard probabilistic δ-GLMB filter to yield joint state, number, and trajectory estimates of multiple appearing and disappearing targets. Beyond that, it is capable to account for epistemic uncertainty due to ignorance or partial knowledge regarding the multi-target system, e.g., the absence of complete information on dynamical model parameters (e.g., probability of detection, birth) and initial number and state of newborn targets. The features of the developed filter are demonstrated using two simulated scenarios.

show abstract

Section: Possibility Generalizedmentioning

confidence: 99%

“…The cardinality of a δ-GLMB UFS is obtained based on (20), i.e., f c (n) = max (I,ξ)∈Fn(L)×Ξ w (I,ξ) . It is clear that the cardinality of a δ-GLMB is a possibility function with maximum equals one.…”

Section: Implementation Of the Possibility Glmb Filtermentioning

confidence: 99%

Possibility Generalized Labeled Multi-Bernoulli Filter for Multi-Target Tracking Under Epistemic Uncertainty

Cai

Houssineau

Jones

et al. 2022

IEEE Trans. Aerosp. Electron. Syst.

View full text Add to dashboard Cite

show abstract

“…In a previous study, B. T. Vo et al [13] demonstrated the δ-generalized label multi-Bernoulli (δ-GLMB) filter. Since the δ-GLMB filter is based on the GLMB density relative to the multi-target measurement probability and is closed under the Chapman-Kolmogorov prediction equation, it could model target states using labeled random finite sets (RFS), allowing the target state to span several time steps and enabling trajectory generation.…”

Section: Introductionmentioning

confidence: 99%

RHM-δ-GLMB Tracking Algorithm on the Focal Plane for UAV Cluster Targets

2023

View full text Add to dashboard Cite

This paper offers a new tracking algorithm for clustered targets of focal plane unmanned aerial vehicles (UAVs) by integrating the random hypersurface model (RHM) model into the δ-generalized label multi-Bernoulli (δ-GLMB) filter to guarantee a robust UAV cluster target tracking on such focal planes. We first investigated the infrared imaging features of UAV cluster targets by emphasizing the target imaging size and dispersion. Next, we designed an elliptical RHM-based measurement model to map the measurement, state parameters, scaling factors, and errors to pseudo-measurement "0", followed by establishing a pseudo-measurement equation to reflect the target's extended shape size. Then, in order to enhance measurement estimation accuracy, the RHM model was implemented with the δ-GLMB filter and Gamma-Gaussian mixture, which can perform a real-time estimate of the targets' centroid motion state and extended state. We also used the grid-based fast density-based spatial clustering of applications with noise (DBSCAN) segmentation algorithm to overcome the distance-based segmentation method restrictions for infrared radiation (IR) measurement data and diminish the algorithm's complexity even more in the measurement update. Extensive simulations demonstrated that this algorithm outperformed existing matching filtering algorithms in the target centroid motion and extended states. Our investigations also revealed that the algorithm was less vulnerable to clutter and more adaptive, making it more straightforward to accomplish reliable tracking of UAV cluster targets.

show abstract

“…A basic observable condition is that the sensor performs a higher order maneuver than all targets [39]. An alternative approach is to use multiple spatially separated sensors for triangulation, that is, the passive MSMTT [40]. But for this approach, the attendant problem is the wellknown ghosting.…”

Section: Introductionmentioning

confidence: 99%

A New Coarse Gating Strategy Driven Multidimensional Assignment for Two-Stage MHT of Bearings-Only Multisensor-Multitarget Tracking

Wei

Duan

Han

et al. 2022

Sensors

View full text Add to dashboard Cite

The problem of two-dimensional bearings-only multisensor-multitarget tracking is addressed in this work. For this type of target tracking problem, the multidimensional assignment (MDA) is crucial for identifying measurements originating from the same targets. However, the computation of the assignment cost of all possible associations is extremely high. To reduce the computational complexity of MDA, a new coarse gating strategy is proposed. This is realized by comparing the Mahalanobis distance between the current estimate and initial estimate in an iterative process for the maximum likelihood estimation of the target position with a certain threshold to eliminate potential infeasible associations. When the Mahalanobis distance is less than the threshold, the iteration will exit in advance so as to avoid the expensive computational costs caused by invalid iteration. Furthermore, the proposed strategy is combined with the two-stage multiple hypothesis tracking framework for bearings-only multisensor-multitarget tracking. Numerical experimental results verify its effectiveness.

show abstract

Robust multi-sensor generalized labeled multi-Bernoulli filter

Cited by 14 publications

References 43 publications

Possibility Generalized Labeled Multi-Bernoulli Filter for Multi-Target Tracking Under Epistemic Uncertainty

Possibility Generalized Labeled Multi-Bernoulli Filter for Multi-Target Tracking Under Epistemic Uncertainty

RHM-δ-GLMB Tracking Algorithm on the Focal Plane for UAV Cluster Targets

A New Coarse Gating Strategy Driven Multidimensional Assignment for Two-Stage MHT of Bearings-Only Multisensor-Multitarget Tracking

Contact Info

Product

Resources

About