Data association in multi-target tracking using belief theory: handling target emergence and disappearance issue

When associating data in the context of multiple target tracking, one is faced with the problem of handling the target emergence and disappearance. In this paper we show that we are able to handle this issue using belief theory based data association method without the introduction of an additional hypothesis to the frame of discernment. Using a specific modelling of belief functions, this is done by detecting and managing a portion of a conflict, which originates from the non-exhaustivity of the frame of discernment. The proposed method is associative and does not rely on the order under which the beliefs are combined. We demonstrate the effectiveness of the proposed method with experiments on simulated data. Additionally, we compare it with the extended world based data association method where a virtual hypothesis is added to the frame of discernment.

[1]  D. Gruyer,et al.  Data association with believe theory , 2000, Proceedings of the Third International Conference on Information Fusion.

[2]  L. Delahoche,et al.  Omnidirectional sensors cooperation for multi-target tracking , 2001, Conference Documentation International Conference on Multisensor Fusion and Integration for Intelligent Systems. MFI 2001 (Cat. No.01TH8590).

[3]  Alessandro Saffiotti,et al.  The Transferable Belief Model , 1991, ECSQARU.

[4]  D. Gruyer,et al.  Heterogeneous multi-criteria combination with partial or full information , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[5]  Eric Brassart,et al.  An Uncertainty Propagation Architecture for the Localization Problem , 2002 .

[6]  Philippe Smets,et al.  Data association in multi‐target detection using the transferable belief model , 2001, Int. J. Intell. Syst..

[7]  Robert J. Dempster,et al.  Combining IMM filtering and MHT data association for multitarget tracking , 1997, Proceedings The Twenty-Ninth Southeastern Symposium on System Theory.

[8]  Najla Megherbi Bouallagu,et al.  Joint audio-video people tracking using belief theory , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[9]  Philippe Smets,et al.  Analyzing the combination of conflicting belief functions , 2007, Inf. Fusion.

[10]  N. Megherbi,et al.  Multimodal data association based on the use of belief functions for multiple target tracking , 2005, 2005 7th International Conference on Information Fusion.