Paper Info
Title
Multi-Hypotheses Tracking using the Dempster-Shafer Theory, application to ambiguous road context
Abstract
We develop a new method to solve ambiguities in tracks-target association in vehicular environments.Previous work with the Dempster-Shafer theory is improved by incorporating conflictual data in a beneficial way.Two Multi-Hypotheses Tracking methods are examined with their pro- and cons.Ambiguity removal is demonstrated with two examples: pedestrians crossing in front of a vehicle-mounted laserscanner, and an overtaking manoeuvre. This paper presents a Multi-Hypotheses Tracking (MHT) approach that allows solving ambiguities that arise with previous methods of associating targets and tracks within a highly volatile vehicular environment. The previous approach based on the Dempster-Shafer Theory assumes that associations between tracks and targets are unique; this was shown to allow the formation of ghost tracks when there was too much ambiguity or conflict for the system to take a meaningful decision. The MHT algorithm described in this paper removes this uniqueness condition, allowing the system to include ambiguity and even to prevent making any decision if available data are poor. We provide a general introduction to the Dempster-Shafer Theory and present the previously used approach. Then, we explain our MHT mechanism and provide evidence of its increased performance in reducing the amount of ghost tracks and false positive processed by the tracking system.
Year
DOI
Venue
2016
10.1016/j.inffus.2015.10.001
Information Fusion
Keywords
Field
DocType
Tracking,Association,Ambiguity,Dempster–Shafer Theory
Uniqueness,Tracking system,Overtaking,Artificial intelligence,Dempster–Shafer theory,Ambiguity,Mathematics,Machine learning
Journal
Volume
Issue
ISSN
29
C
1566-2535
Citations 
PageRank 
References 
11
0.88
5
Authors
4
Name
Order
Citations
PageRank
Dominique Gruyer148552.30
Sébastien Demmel2394.79
Valentin Magnier3131.24
Rachid Belaroussi49213.17