Bayesian and Dempster-Shafer target identification for radar surveillance

Leung, Henry; Wu, Jiangfeng

doi:10.1109/7.845221

Cited by 65 publications

(39 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods have several pitfalls of its own, such as it weakness in handling faults data inputs efficiently, it cannot distinguish if the data coming from the sensors are correctly found or it wrong due to the environmental noise or even sensor damaged, and that might cause some incorrect estimation [19]. Moreover, to overcome such a pitfall an generalization method of Bayesian is developed which called The Dempster-Shafer method, it overcome and uncertainly of Bayesian method, one of the main difference between the Dempster-Shafer method and Bayesian method is that the Dempster-Shafer method uses the combination of an events instead individual event like in Bayesian and that what make it more flexible, however in a comparative study applied in air surveillance [20] showed that both of the method had the ability to track and object correctly and the only difference is that the implementation of Bayesian method was more simpler and had more probabilities for the correct decision, while Dempster-Shafer method showed more sturdiness in noise and imprecise prior information disturbance. However, the modified method of Bayesian method showed more efficient, extensible, and theoretically acceptable method for managing uncertainty [19].…”

Section: Evaluation Of Decision Methodsmentioning

confidence: 99%

A Review of Data Fusion Techniques

Alofi¹,

Alghamdi²,

Alahmadi³

et al. 2017

IJCA

View full text Add to dashboard Cite

In many cases, researchers use more than one sensor and synthesize their raw data to generate more meaningful information that can be of greater value than single source data. The process of merging multiple data and knowledge from different sources to represent the object into a regular, accurate, useful, meaningful representation is known as data fusion. This article summarizes the state of data fusion and compares relevant techniques. We explain possible data fusion classifications and review the most common fusion methods such as Kalman filter and The Bayesian Methods. Then we evaluate these methods and discuss the advantages and disadvantages of each method. General TermsMulti-sensor fusion, data fusion, Kalman filter, Particle filter, Bayesian methods, Dempster-Shafer.

show abstract

Section: Evaluation Of Decision Methodsmentioning

confidence: 99%

A Review of Data Fusion Techniques

Alofi¹,

Alghamdi²,

Alahmadi³

et al. 2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Comparative studies of these techniques have been published in the specialized literature [5]. The inferences for their advantages and disadvantages are usually conflicting.…”

Section: Introductionmentioning

confidence: 99%

“…Several methods such as Bayesian [1][2][3][4], Dempster-Shafer [5,6] methods and fuzzy set theory [7] have been applied to solve different identification problems. Comparative studies of these techniques have been published in the specialized literature [5].…”

Section: Introductionmentioning

confidence: 99%

Joint target tracking and classification with particle filtering and mixture Kalman filtering using kinematic radar information

Angelova

Mihaylova

2006

Digital Signal Processing

View full text Add to dashboard Cite

This paper considers the problem of joint maneuvering target tracking and classification. Based on recently proposed Monte Carlo techniques, a multiple model (MM) particle filter and a mixture Kalman filter (MKF) are designed for two-class identification of air targets: commercial and military aircraft. The classification task is carried out by processing radar measurements only, no class (feature) measurements are used. A speed likelihood function for each class is defined using a prior information about speed constraints. Class-dependent speed likelihoods are calculated through the state estimates of each class-dependent tracker. They are combined with the kinematic measurement likelihoods in order to improve the classification process. The two designed estimators are compared and evaluated over rather complex target scenarios. The results demonstrate the usefulness of the proposed scheme for the incorporation of additional speed information. Both filters illustrate the opportunity of the particle filtering and mixture Kalman filtering to incorporate constraints in a natural way, providing reliable tracking and correct classification. Future observations contain valuable information about the current state of the dynamic systems. In the framework of the MKF, an algorithm for delayed estimation is designed for improving the current modal state estimate. It is used as an additional, more reliable information in resolving complicated classification situations.

show abstract

“…In terms of target tracking, significant advancements have been made in the past two decades to improve tracking technology by employing sophisticated data fusion techniques. Some of the earlier works went even further by incorporating Target Identification information, such as IFF data, to improve the overall track quality (Leung & Wu, 2000), (Carson & Peters, 26-30 Oct 1997), (Bastiere, 1997), and (Perlovsky & Schoendorf, 1995). When legitimate statistical information is presented, the techniques employed by tracking and identification using IFF information are relatively mature.…”

Section: Introductionmentioning

confidence: 99%