Re-identification by Inductive Loop Detector: Experimentation on target origin - Destination matrix

David Guilbert (1) , Cédric Le Bastard (1) , Sio Song Ieng (2) , Yide Wang (1)

1 IETR - Institut d'Électronique et des Technologies du numéRique
2 IFSTTAR/LEPSIS - Laboratoire Exploitation, Perception, Simulateurs et Simulations

Traffic congestion has led to research on how to use the existing infrastructure more efficiently. The experimental platform SAROT was constructed to allow traffic analysis but also to test new algorithms for traffic modeling and management. Origin-Destination (OD) Matrix is one of the most important traffic information for Intelligent Traffic System. By using the experimental platform SAROT, we want to test algorithms for OD Matrix. To obtain OD matrix, we need to get useful and accurate data by tracking vehicles. Two approaches for tracking vehicles by using Inductive Loop Detector (ILD) are used. Both approaches are computed on real traffic data set and compared. We use threshold decision to improve the correct matching rate for tracking vehicles. We propose a new methodology by associating two algorithms for increasing the correct matching rate. The new methodology was used to perform target OD matrix.

Mots clés: Modélisation; Trafic routier; Localisation

Domaines: Sciences de l'ingénieur [physics]

David Guilbert, Cédric Le Bastard, Sio Song Ieng, Yide Wang. Re-identification by Inductive Loop Detector: Experimentation on target origin - Destination matrix. IEEE Intelligent Vehicles Symposium, Jun 2013, Gold Coast, Australia. 6p, ⟨10.1109/IVS.2013.6629666⟩. ⟨hal-00795232⟩