Real-time neural vision for obstacle detection using linear cameras
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 524-529
- https://doi.org/10.1109/ivs.1995.528336
Abstract
This paper presents a neural vision system for real-time obstacle detection in front of vehicles using a linear stereo vision set-up. The problem addressed here consists in identifying features in two images that are projections of the same physical entity in the three-dimensional world. The linear stereo correspondence problem is formulated as an optimization problem. An energy function, which represents the constraints on the solution, is mapped onto a two-dimensional Hopfield neural network for minimization. The system has been evaluated with experimental results on real stereo images.Keywords
This publication has 4 references indexed in Scilit:
- A New Edge Matching Procedure For Obstacle Detection By Linear Stereo VisionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Hopfield network for stereo vision correspondenceIEEE Transactions on Neural Networks, 1992
- Fast algorithms for low-level visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- “Neural” computation of decisions in optimization problemsBiological Cybernetics, 1985