PERCEPTUAL ARCHITECTURE FOR A VISION SYSTEM OF AUTONOMOUS VEHICLES

This paper presents a perceptual architecture for a dynamic vision system for autonomous vehicles. The architecture is based on a framework which defines a solid representation of objects. The paper first describes the vehicles and the types of scenarios for the autonomous vehicles. The perceptual architecture is then described including its three layers: the situation, object, and feature, which constitute the framework upon which the architecture relies. A brief review of the implementation of the architecture is presented followed by suggestions for futures applications.

• Supplemental Notes:
  • Publication Date: 1998. IEEE Service Center, Piscataway NJ. Remarks: Also available on the DaimlerBenz website at URL: http://www.daimlerbenz.com/research/events/iv98.html. Format: website
• Corporate Authors:

  Ruhr-Universitat Bochum. Institut fur Neuroinformatik

  ,    

  Universita di Parma Dipartimento di ingegneria dell informazione

  ,    

  Sumitomo Denki Kogyo Kabushiki Kaisha

  ,    

  Chalmers University of Technology, Sweden

  Department of Applied Mechanics/CHARMEC
  Gothenburg,   Sweden 

  Ohio State University, Columbus

  Center for Intelligent Transportation Research
  Columbus, OH  United States  43210

  Honda Gijutsu Kenkyujo

  ,    

  Universitat der Bundeswehr Munchen. Institut fur Systemdynamic und Flugmechanik

  ,    

  Daimler-Benz Forschungszentrum

  ,    

  Ceske vysoke uceni technicke v Praze

  ,    
• Authors:
  • Holt, Volker von
  • Baten, Stefan
• Conference:
  • IEEE International Conference on Intelligent Vehicles. Proceedings of the 1998 IEEE International Conference on Intelligent Vehicles.
  • Location: Stuttgart , Germany
  • Date: 1998-0-0
• Publication Date: 1998

Language

• English

Media Info

• Pagination: p. 539-544
• Serial:
  • Volume: 2

Subject/Index Terms

• TRT Terms: Advanced vehicle control systems; Computer vision; System architecture; System design
• Subject Areas: Operations and Traffic Management;

Filing Info

• Accession Number: 00813276
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Jul 5 2001 12:00AM