Coupled detection, association and tracking for Traffic Sign Recognition

Mohammed Boumediene (1) , Jean-Philippe Lauffenburger (2) , Jérémie Daniel (2) , Christophe Cudel (3)

1 Laboratoire Signaux et Images
2 IRIMAS - Institut de Recherche en Informatique Mathématiques Automatique Signal
3 MIPS - Modélisation, Intelligence, Processus et Système

— This paper tackles the problem of tracking-based Traffic Sign Recognition (TSR) systems. It presents an integrated object detection, association and tracking approach based on a spatio-temporal data fusion. This algorithm tracks detected sign candidates in order to reduce false positives. Regions Of Interest (ROIs) potentially containing traffic signs are determined from the vehicle-mounted camera images. An original corner detector associated to pixel coding ensures the detection efficiency. The ROIs are combined using the Transfer-able Belief Model semantics. The associations maximizing the pairwise belief between the detected ROIs and ROIs tracked by multiple Kalman filters are processed. The track evolution helps to detect false positives. Thanks to this solution and to a feedback loop between the tracking algorithm and the ROI detector, a false positive reduction of 45% is assessed.

Mots clés: Data association; Tracking; Extended Kalman filter; Traffic sign recognition

Domaines: Traitement du signal et de l'image [eess.SP]; Automatique / Robotique

Mohammed Boumediene, Jean-Philippe Lauffenburger, Jérémie Daniel, Christophe Cudel. Coupled detection, association and tracking for Traffic Sign Recognition. Intelligent Vehicles Symposium, IEEE, Jun 2014, Dearborn, United States. ⟨10.1109/IVS.2014.6856492⟩. ⟨hal-01123469⟩