This paper presents Fade, a vehicle detection and tracking system featuring monocular color vision and radar data fusion. Its main originality resides in its low-level fusion system. At each step and for each target, the fusion system fuses the results of four different image processing algorithms and radar information by automatically combining 12 different features and generating many possible target position proposals. It generates a belief network organized in three layers: sources, position proposals, and correlation between proposals. An inference algorithm is then used to find out the actual position of the target, by deducing which observations are wrong. The overall system runs in real time and has been evaluated on a variety of scenarios recorded in a real car using /sup RT/Maps. Fade yields very good detection results in most cases.
Fade: a vehicle detection and tracking system featuring monocular color vision and radar data fusion
Intelligent Vehicle Symposium, 2002. IEEE ; 2 ; 632-639 vol.2
01.01.2002
421414 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Fade: A Vehicle Detection and Tracking System Featuring Monocular Color Vision and Radar Data Fusion
British Library Conference Proceedings | 2003
|Moving vehicle detection and tracking using monocular vision
Kraftfahrwesen | 2014
|Moving vehicle detection and tracking using monocular vision
Tema Archiv | 2014
|Moving vehicle detection and tracking using monocular vision
Online Contents | 2014
|Tracking RGB Color Markers through DLT Calibrated Monocular Vision System
British Library Conference Proceedings | 2016
|