Suqi Li

Distributed Fusion With Multi-Bernoulli Filter Based on Generalized Covariance Intersection

In this letter, we consider the distributed multi-target tracking through the use of multi-Bernoulli based on generalized Covariance Intersection (G-CI). However, the G-CI fusion of two multi-Bernoulli posterior distributions does not admit an closed-form expression. To solve this problem, we firstly approximate the fused posterior as an unlabeled version of δ-generalized labelled multi-Bernoulli (δ-GLMB) distribution, referred to as δ-GMB. To allow the subsequent fusion with another multi-Bernoulli distribution, e.g., fusion with a third sensor node in the sensor network, or feedback working mode, we further approximate the fused δ-GMB posterior using a multi-Bernoulli formed distribution which matches its first-order statistical moment. We implement the proposed method using sequential Monte Carlo techniques and demonstrate its performance in two challenging tracking scenarios.

Robust Distributed Fusion With Labeled Random Finite Sets

This paper considers the problem of the distributed fusion of multiobject posteriors in the labeled random finite set filtering framework, using a generalized covariance intersection (GCI) method. Our analysis shows that GCI fusion with labeled multiobject densities strongly relies on label consistencies between local multiobject posteriors at different sensor nodes, and hence suffers from a severe performance degradation when perfect label consistencies are violated. Moreover, we mathematically analyze this phenomenon from the perspective of the principle of minimum discrimination information and the so-called yes-object probability. Inspired by the analysis, we propose a novel and general solution for the distributed fusion with labeled multiobject densities that is robust to label inconsistencies between sensors. Specifically, the labeled multiobject posteriors are first marginalized to their unlabeled posteriors, which are then fused using the GCI method. We also introduce a principled method to construct the labeled fused density and produce tracks formally. Based on the developed theoretical framework, we present tractable algorithms for the family of generalized labeled multi-Bernoulli (GLMB) filters including

Distributed sensor fusion for RFS density with consideration of limited sensing ability

\delta

Dynamic factorization based multi-target Bayesian filter for multi-target detection and tracking

-GLMB, marginalized

Distributed Joint Attack Detection and Secure State Estimation

\delta

Multiobject Tracking for Generic Observation Model Using Labeled Random Finite Sets

-GLMB, and labeled multi-Bernoulli filters. The robustness and efficiency of the proposed distributed fusion algorithm are demonstrated in challenging tracking scenarios via numerical experiments.

Multiple sensor Multi-Bernoulli filter based track-before-detect for polarimetric MIMO radars

The paper addresses the problem of distributed sensor fusion in the framework of random finite set. The Generalized Covariance Intersection (GCI) rule of multi-target densities is extensively used in multi-target Bayesian filtering scheme. But there are two problems in GCI which are unreasonable design of fusion weight and unable to tackle informative differentiation. In order to get rid of the bad influence of these two problems, we propose a heuristic Heuristic distributed fusion (HDF) method by two steps: fusion weight reconstruction and information difference preservation. Finally, we compare the GCI fusion with our proposed HDF method in two scenarios. The results show that HDF is more robust and can achieve better performance.

Distributed fusion with multi-Bernoulli filter based on generalized Covariance Intersection

This paper considers the problem of simultaneously detecting and tracking multiple targets based on the unthres-holed, track-before-detect style measurement model. The problem is formulated in a Bayesian framework by modeling the collection of states as a random finite set. [1] is the pioneer addressing this problem. However, the application of this work is largely restricted by its independence assumption which only holds when targets are well separated. This paper is committed to generalize this method to accommodate the arbitrary placement of targets. To this end, we propose a dynamic factorization based multitarget Bayesian filter which utilizes independence between targets whenever possible, while considers target estimation jointly when target states exhibit correlation. A novel sequential Monte Carlo implementation for the proposed multi-target Bayesian filter is also presented. Simulation results for a scenario with two crossing targets show the superior performance of the proposed filter.

A polarization information aided probabilistic data association for target tracking in polarimetric radar system

The joint task of detecting attacks and securely monitoring the state of a cyber-physical system is addressed over a cluster-based network wherein multiple fusion nodes collect data from sensors and cooperate in a neighborwise fashion in order to accomplish the task. The attack detection–state estimation problem is formulated in the context of random set theory by representing joint information on the attack presence/absence, on the system state, and on the attack signal in terms of a hybrid Bernoulli random set (HBRS) density. Then, combining previous results on HBRS recursive Bayesian filtering with novel results on Kullback–Leibler averaging of HBRSs, a novel distributed HBRS filter is developed and its effectiveness is tested on a case study concerning wide-area monitoring of a power network.

Polarimetric MIMO radar detection for correlated fluctuating targets

This paper presents an exact Bayesian filtering solution for the multiobject tracking problem with the generic observation model. The proposed solution is designed in the labeled random finite set framework, using the product styled representation of labeled multiobject densities, with the standard multiobject transition kernel and no particular simplifying assumptions on the multiobject likelihood. Computationally tractable solutions are also devised by applying a principled approximation involving the replacement of the full multiobject density with a labeled multi-Bernoulli density that minimizes the Kullback–Leibler divergence and preserves the first-order moment. To achieve the fast performance, a dynamic-grouping-procedure-based implementation is presented with a step-by-step algorithm. The performance of the proposed filter and its tractable implementations are verified and compared with the state of the art in numerical experiments.