The problem tackled in this paper deals with obstacle tracking in the context of vehicle driving aid, especially the association step, which consists in associating perceived objects with known objects detected at a previous time. A contribution in the modeling of this association problem in the belief function framework is introduced. By interpreting belief functions as weighted opinions according to the Transferable Belief Model semantics, pieces of information regarding the association of known objects and perceived objects can be expressed in a common global space of association to be combined by the conjunctive rule of combination, and a decision making process using the pignistic transformation can be made. This approach is validated on real data.
Keywords. Obstacle tracking, association step, belief functions, Transferable Belief Model
Paper Download
The paper is availabe in the following formats:
Plenary talk : Press here to get the file of the presentation.
Poster : Press here to get the file of the poster.
Authors addresses:
David Mercier
LGI2A EA 3926
Université d'Artois
Technoparc Futura
62400 BETHUNE
France
Eric Lefevre
LGI2A EA 3926
Université d'Artois
Technoparc Futura
62400 Béthune
France
E-mail addresses:
| David Mercier | david.mercier@univ-artois.fr |
| Eric Lefevre | eric.lefevre@univ-artois.fr |