Camera based vehicle detection and tracking using shadows and adaptive template matching

Enhancement of road traffic safety means that the human component as well as the technical components have to work at highest level. Together they build a complex system. Due to rising road traffic, mental and physical stress, driver's concentration is deteriorating and is the main reason for traffic accidents. Improvement of the human factor is very difficult, but the introduction of driver assistance systems offers a wide range of applications that help to compensate or correct human faults. Typical accidents, caused by missing driver's attention, are accidents during lane change. Drivers forget to assure that no other vehicle is alongside; especially they forget to check the blind spot. This paper presents our first approaches to detect vehicles in the blind spot of a driving car.

[1]  Amnon Shashua,et al.  Vision-based ACC with a single camera: bounds on range and range rate accuracy , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[2]  Hideo Mori,et al.  Shadow and rhythm as sign patterns of obstacle detection , 1993, ISIE '93 - Budapest: IEEE International Symposium on Industrial Electronics Conference Proceedings.

[3]  Reinhold Behringer,et al.  The seeing passenger car 'VaMoRs-P' , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[4]  Thomas Kalinke,et al.  A Texture-based Object Detection and an adaptive Model-based Classification , 1998 .

[5]  Larry S. Davis,et al.  Multiple vehicle detection and tracking , 1997, Other Conferences.

[6]  Gianni Conte,et al.  Automatic Vehicle Guidance: the Experience of the ARGO Autonomous Vehicle , 1999 .