Laboratoire de Génie Informatique et d’Automatique de l’Artois

Samir HACHOUR

Associate professor
Member of the research axes:
2015
Scientific book
Belief function based multisensor multitarget classification solution
Multisensor data fusion, From algorithms and architectural design to applications, pp 331-348, H. Fourati (Ed.), CRC Press, août 2015
Object tracking and credal classification with kinematic data in a multi-target context
Information Fusion, pp 174-188, Vol. 20, , novembre 2014
A new parameterless credal method to track-to-track assignment problem
3rd International Conference on Belief Functions, BELIEF 2014, pp 403-411, Oxford, United Kingdom, F. Cuzzolin (Ed.), septembre 2014
A distributed solution for multi-object tracking and classification
17th International Conference on Information Fusion, FUSION 2014, Salamanca, Spain, , paper 323, juillet 2014
2014
International conference with review committee
Comparison of credal assignment algorithms in kinematic data tracking context
15th Information Processing and Management of Uncertainty in Knowledge-Based Systems International Conference, IPMU 2014, pp 200-211, Montpellier, France, juillet 2014
Multi-Sensor multi-target tracking with robust kinematic data based credal classification
8th Workshop, Sensor Data Fusion: Trends, Solutions, Application , SDF 2013, Bonn, Germany, octobre 2013
2013
French conference with review committee
Fusion d’Informations pour la Classification Multi-capteurs, Multi-cibles
22èmes Rencontres Francophones sur la Logique Floue et ses Applications , 10-11 octobre , LFA 2013, pp 111-118, Reims, janvier 2013
Tracking and Identification of Multiple Targets
7ème Workshop Interdisciplinaire sur la Sécurité Globale, WISG, No. 13, Troyes, France, janvier 2013
Classification crédale multi-cibles
21e Rencontres Francophones sur la Logique Floue et ses Applications (LFA 2012), pp 201-208, Compiègne, France, novembre 2012

Author of the Ph.D. thesis "Multi-object tracking and classification : contributions with belief functions theory"

2011 - 2015

This thesis deals with multi-objet tracking and classification problem. It was shown that belieffunctions allow the results of classical Bayesian methods to be improved. In particular, a recentapproach dedicated to a single object classification which is extended to multi-object framework. Itwas shown that detected observations to known objects assignment is a fundamental issue in multiobjecttracking and classification solutions. New assignment solutions based on belief functionsare proposed in this thesis, they are shown to be more robust than the other credal solutions fromrecent literature. Finally, the issue of multi-sensor classification that requires a second phase ofassignment is addressed. In the latter case, two different multi-sensor architectures are proposed, aso-called centralized one and another said distributed. Many comparisons illustrate the importanceof this work, in both situations of constant and changing objects classes.

GS2RI (ELSAT 2020)

2015 - 2020

Greener and Safer Rail Road Interaction

Summary :

L’objet du projet PSCHITT_Rail est de réaliser la co-simulation ferroviaire dans un réseau urbain entre des tramways d’une part, et des véhicules et piétons d’autre part, dans le but d’améliorer la sécurité des usagers.