Visual Surveillance for Moving Vehicles

An overview is given of a novel vision system for locating, recognising and tracking multiple vehicles, using a single monocular camera mounted on a moving vehicle1 . 3D model-based techniques are employed to obtain detailed information about vehicle movements. Egomotion estimation is performed by inter-frame tracking of features on the ground plane. Vehicle detection and hypothesis generation is performed using a template correlation technique. Once detected and identified, vehicles are tracked using dynamic filtering. The resulting information about 3-D vehicle motions is passed to a collision alert system which can warn the driver of potential hazards. The overall approach is demonstrated on a typical motorway image sequence.

• Type: Journal
• Year: 2000
• Where: IJCV
• Authors: James M. Ferryman, Stephen J. Maybank, Anthony D. Worrall
• Keywords: IJCV 2000, Single Monocular Camera, Template Correlation Technique, Vehicle