a The cost of machine vision systems is limiting their applications. The goal of this project is to develop cost-effective vision systems for a number of intelligent vehicle applications. The authors propose concurrent design of algorithms and hardware as a way of improving the cost and performance of vision systems. With this approach, the authors develop custom hardware rather than using off-the-shelf microprocessors. This paper describes three example systems which the authors have developed or are developing: car following, lane detection, and stereo vision. With the car following system, a driver pushes a button when he or she has a car in front which he/she would like to follow. The vehicle speed is controlled automatically using a vision system to keep a constant distance to the car in front. This system is described in section 2. Section 3 is devoted to the lane sensing vision system. Both the car following and lane sensing systems were implemented using custom digital hardware (described in section 4) at General Motors when the first author was working with GM. The stereo vision system in section 5 is currently being developed by a group at Massachusetts Institute of Technology. A feature of this stereo vision system is that it uses analog/digital hybrid technology to reduce system cost without sacrificing performance.
Cost-effective vision systems for intelligent vehicles
Kostengünstiges maschinelles Sehen für intelligente Fahrzeuge
1994
5 Seiten, 6 Bilder, 5 Quellen
Conference paper
English
Cost-Effective Vision Systems for Intelligent Vehicles
British Library Conference Proceedings | 1994
|Vision for Intelligent Road Vehicles
British Library Conference Proceedings | 1993
|Real time vision for intelligent vehicles
Tema Archive | 2001
|Vision-based perception for intelligent vehicles
IEEE | 2015
|