The Community for Technology Leaders
Proceedings IEEE Workshop on Applications of Computer Vision (1992)
Palm Springs, CA, USA
Nov. 30, 1992 to Dec. 2, 1992
ISBN: 0-8186-2840-5
pp: 100-109
G.-S. Young , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
T.-H. Hong , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
M. Herman , Nat. Inst. of Stand. & Technol., Gaithersburg, MD, USA
ABSTRACT
To operate autonomous vehicles safely, obstacles must be detected before any path planning and obstacle avoidance activity is undertaken. In the paper, a novel approach to obstacle detection is developed. New visual linear invariants based on optical flow have been developed. Employing the linear invariance property, obstacles an be directly detected by using a reference flow line obtained from measured optical flow. This method can be used for ground vehicles to navigate through man-made roadways or natural outdoor terrain or for air vehicles to land on known or unknown terrain.<>
INDEX TERMS
computer vision, mobile robots
CITATION

G. Young, T. Hong, M. Herman and J. Yang, "New visual invariants for obstacle detection using optical flow induced from general motion," Proceedings IEEE Workshop on Applications of Computer Vision(ACV), Palm Springs, CA, USA, , pp. 100-109.
doi:10.1109/ACV.1992.240322
96 ms
(Ver 3.3 (11022016))