Self-organizing neural network architectures for computing visual depth from motion parallax
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 227-234 vol.2
- https://doi.org/10.1109/ijcnn.1989.118703
Abstract
The analysis describes some of the issues involved in constructing a self-organizing neural network that can learn to perform a high-level vision task, depth perception from motion parallax, without guidance from an external teacher. An examination is made of how motion parallax conveys depth information. A network structure is presented for detecting and representing depth from motion parallax. How a depth-sensitive network can self-organize is also examined.Keywords
This publication has 55 references indexed in Scilit:
- A massively parallel architecture for a self-organizing neural pattern recognition machinePublished by Elsevier ,2005
- Local circuit neurons of macaque monkey striate cortex: I. Neurons of laminae 4C and 5AJournal of Comparative Neurology, 1987
- Effects of foveal priming and extrafoveal preview on object identification.Journal of Experimental Psychology: Human Perception and Performance, 1987
- Visual processing of motionTrends in Neurosciences, 1986
- Facilitatory Interactions between Flashed LinesPerception, 1986
- Intrinsic laminar lattice connections in primate visual cortexJournal of Comparative Neurology, 1983
- Anatomical banding of intrinsic connections in striate cortex of tree shrews (Tupaia glis)Journal of Comparative Neurology, 1982
- Widespread Periodic Intrinsic Connections in the Tree Shrew Visual CortexScience, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- Motion Parallax as an Independent Cue for Depth PerceptionPerception, 1979