This implementation of lane and obstacle detection for an autonomous, self-guided vehicle succeeds by tailoring vision and computational techniques to an affordable SIMD architecture. The authors use a geometrical transform called inverse perspective mapping (IPM). Using a priori knowledge of both the scene and the acquisition device, the IPM technique allows one to remove the perspective effect and produce a new image in which the information content is homogeneously distributed among all pixels. In the remapped image, the amount of information carried by each pixel no longer depends on the pixel's position, making the SIMD approach practical.
Vision-based vehicle guidance
Fahrzeugsteuerung auf der Basis maschinellen Sehens
Computer, Long Beach ; 30 , 7 ; 49-55
1997
7 Seiten, 10 Quellen
Article (Journal)
English
SLUB | 1992
|TIBKAT | 1992
|ASIC approaches for vision-based vehicle guidance
Tema Archive | 1993
|VLSI chips for vision-based vehicle guidance
SPIE | 1994
|High Speed Vehicle Guidance Based on Vision
British Library Conference Proceedings | 1993
|