Title :
An association algorithm for tracking multiple moving objects
Author :
Lemeret, Yann ; Lefevre, Eric ; Jolly, Daniel
Author_Institution :
Faculte des Sci. Appliquees, Univ. d´´Artois, Bethune
Abstract :
In the field of intelligent vehicle and in order to raise the road safety, an improvement of the driver´s assistance, more particularly obstacles detection systems, is presented. Objects are detected with sensors laid out on a car, and are then tracked thanks to an association algorithm. Rombaut (1998) association algorithm has been modified in order to have a better decision when data reliability decreases or if one sensor fails. This paper presents Rombaut (1998) association algorithm and the modification made on it. Then, a comparison between the two association algorithms for a decreasing data reliability is made using simulated data. Finally the robustness of the two algorithms was tested with data coming from a CCD camera
Keywords :
fault tolerant computing; image motion analysis; object detection; road safety; target tracking; traffic engineering computing; Rombaut association algorithm; data reliability; decision making; driver assistance; intelligent vehicle; multiple moving object tracking; obstacles detection systems; road safety; Intelligent sensors; Intelligent vehicles; Laboratories; Laser radar; Object detection; Radar detection; Radar tracking; Road safety; Robustness; Vehicle detection;
Conference_Titel :
Intelligent Transportation Systems Conference, 2006. ITSC '06. IEEE
Conference_Location :
Toronto, Ont.
Print_ISBN :
1-4244-0093-7
Electronic_ISBN :
1-4244-0094-5
DOI :
10.1109/ITSC.2006.1707408