Object-level fusion and confidence management in a multi-sensor pedestrian tracking system
Résumé
This paper describes a multi-sensor fusion system dedicated to detect, recognize and track pedestrians. The fusion by tracking method is used to fuse asynchronous data provided by different sensors with complementary and supplementary fields of view. Having the performance of the sensors, we propose to differentiate between the two problems: object detection and pedestrian recognition, and to quantify the confidence in the detection and recognition processes. This confidence is calculated based in geometric features and it is updated under the Transferable Belief Model framework. The vehicle proprioceptive data are filtered by a separate Kalman filter and are used in the estimation of the relative and absolute state of detected pedestrians. Results are shown with simulated data and with real experimental data acquired in urban environment
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...