Robust vehicle detection at large distance using low resolution cameras

Author

Knoeppel, C. ; Chanz, A.S. ; Michaelis, B.

Author_Institution

Res. Inst., DaimlerChrysler AG, Esslingen, Germany

fYear

2000

fDate

2000

Firstpage

267

Lastpage

272

Abstract

This paper describes a robust vehicle detection system which detects vehicles in the rear view of the host car. Two cameras with 12 mm focal length mounted behind the back pane are used. Reliable vehicle recognition up to 150 m and the exact track localization of the vehicles are the key features of the system. The robust stereo algorithm generates object hypotheses which are tracked with Kalman filter. Using the steering angle and the detected obstacles, the driven way of the host vehicle is reconstructed. This information is used for a lane change assistant

Keywords

Kalman filters; computer vision; driver information systems; filtering theory; image recognition; image reconstruction; object detection; road vehicles; stability; stereo image processing; tracking; 12 mm; 150 m; Kalman filter; exact track localization; lane change assistant; low resolution cameras; robust stereo algorithm; robust vehicle detection system; steering angle; Cameras; Change detection algorithms; Object detection; Object recognition; Radar detection; Radar tracking; Robustness; Vehicle detection; Vehicle driving; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Vehicles Symposium, 2000. IV 2000. Proceedings of the IEEE

Conference_Location

Dearborn, MI

Print_ISBN

0-7803-6363-9

Type

conf

DOI

10.1109/IVS.2000.898353

Filename

898353