In this paper we describe a multi-camera traffic monitoring system relying on the concept of probability fusion maps (PFM) to detect vehicles in a traffic scene. In the PFM, traffic images from multiple cameras are inverse-mapped and registered onto a common reference frame, combining the multiple camera information to reduce the impact of occlusions. The perspective projection is, generally, non-invertible, although imposing the constraint that the image points be co-planar allows inversion. However, in a traffic scene, the co-planarity of image points is not strictly true, so the PFM are subject to distortions. We present a new approach to reducing these distortions by projecting the camera images onto planes at different offsets from the road plane. These PFM are combined to generate a multi-level (ML) PFM. We show that the distortions in the various projection planes offset and the ML PFM thus improves vehicle detection in the presence of occlusions.
Vehicle detection using multi-level probability fusion maps generated by a multi-camera system
2008 IEEE Intelligent Vehicles Symposium ; 452-457
2008-06-01
431170 byte
Conference paper
Electronic Resource
English
Vehicle Detection Using Multi-Level Probability Fusion Maps Generated by a Multi-Camera System
British Library Conference Proceedings | 2008
|Recursive building of local maps using multi level feature fusion
Tema Archive | 2007
|Multi-sensor obstacle existence probability fusion method and vehicle
European Patent Office | 2025
|Parking space detection system based on multi-camera fusion
European Patent Office | 2022
|