A second-order uncertainty model for target classification using kinematic data

Mei, Wei; Shan, Ganlin; Wang, Yuefeng

doi:10.1016/j.inffus.2010.03.004

Cited by 14 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. Update: if the multi-target prediction density is a GLMB has the form as (11), the multi-target posterior density is then also a GLMB and has the following form:…”

Section: Marginal Generalized Labeled Multi-bernoulli Filtermentioning

confidence: 99%

“…In [ 10 ], particle filter is introduced into TBM framework to solve target joint tracking and classification problem in multi-sensor scenario. In [ 11 ], a second-order uncertainty model is proposed to describe the uncertain mapping from the dynamic feature space to the target class space, and a practical method based on TBM is provided to calculate the class likelihood under a relaxed dependence assumption. However, due to the discrete nature of such set theoretic uncertain reasoning approaches based on TBM, these algorithms have difficulty in modeling continuous signals.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Target Joint Detection; Tracking and Classification Based on Marginal GLMB Filter and Belief Function Theory

Liang

Jing

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper proposes a new solution to multi-target joint detection, tracking and classification based on labeled random finite set (RFS) and belief function theory. A class dependent multi-model marginal generalized labeled multi-Bernoulli (MGLMB) filter is developed to analytically calculate the multi-target number, state estimates and model probabilities. In addition, a two-level classifier based on continuous transferable belief model (cTBM) is designed for target classification. To make full use of the kinematic characteristics for classification, both the dynamic modes and states are considered in the classifier, the model dependent class beliefs are computed on the continuous state feature subspace corresponding to different dynamic modes and then fused. As a result that the uncertainty about the classes is well described for decision, the classification results are more reasonable and robust. Moreover, as the estimation and classification problems are jointly solved, the tracking and classification performance are both improved. In the simulation, a scenario contains multi-target with miss detection and dense clutter is used. The performance of multi-target detection, tracking and classification is better than traditional methods based on Bayesian classifier or single model. Simulation results are illustrated to demonstrate the effectiveness and superiority of the proposed algorithm.

show abstract

“…2. Update: if the multi-target prediction density is a GLMB has the form as (11), the multi-target posterior density is then also a GLMB and has the following form:…”

Section: Marginal Generalized Labeled Multi-bernoulli Filtermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-Target Joint Detection; Tracking and Classification Based on Marginal GLMB Filter and Belief Function Theory

Liang

Jing

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…1 [9]. The first stage, uncertain mapping Ⅰ, is to select/extract features from observation information.…”

Section: Uncertainty Modeling For Target Recognitionmentioning

confidence: 99%

Model the uncertainty in target recognition using possiblized bayes' theorem

Mei¹,

Shan²,

Wang³

2012

2012 IEEE International Conference on Fuzzy Systems

Self Cite

View full text Add to dashboard Cite

Abstract-The major source of uncertainty in target recognition consists of two parts. One is about feature extraction from observation data and another is about the rule definition between target type and feature. While the former can be naturally captured in the form of statistics, it is our opinion that the latter should be defined by using possibility since exact probability assignment is in general impossible. This paper addresses target recognition within the Bayesian framework while reinterpreting the likelihood of Bayes' theorem as a possibility. It leads to an open structure of feature database, which can exempt the reconstruction of feature database of the Bayesian classifier when new feature rules need to be included. An example of target recognition using attribute data from an electronic support measure (ESM) shows that the proposed method has competitive performance with the conventional Bayesian classifier.

show abstract

“…A full multi-target tracking solution includes several interlaced components such as the tracking component, the assignment component, the hypothesis rejection (new or disappeared targets...) and finally the classification step. Probability-based solutions already exist in the literature [1,2,3,4,5,6,7].…”

Section: Introductionmentioning

confidence: 99%

Object tracking and credal classification with kinematic data in a multi-target context

et al. 2014

View full text Add to dashboard Cite

This article proposes a method to classify multiple maneuvering targets at the same time. This task is a much harder problem than classifying a single target, as sensors do not know how to assign captured measurements to known targets. This article extends previous results scattered in the literature and unifies them in a single global framework with belief functions. Through two examples, it is shown that the full algorithm using belief functions improves results obtained with standard Bayesian classifiers and that it can be applied to a large variety of applications.

show abstract

A second-order uncertainty model for target classification using kinematic data

Cited by 14 publications

References 17 publications

Multi-Target Joint Detection; Tracking and Classification Based on Marginal GLMB Filter and Belief Function Theory

Multi-Target Joint Detection; Tracking and Classification Based on Marginal GLMB Filter and Belief Function Theory

Model the uncertainty in target recognition using possiblized bayes' theorem

Object tracking and credal classification with kinematic data in a multi-target context

Contact Info

Product

Resources

About