Properties of independent components of self-motion optical flow

In this paper we describe the properties of independent components of optical flow of moving objects. Video sequences of objects seen by an observer moving at various angles, directions and distances are used to produce optical flow maps. These maps are then, recessed using independent component ana...

Full description

Saved in:
Bibliographic Details
Main Authors: Jabri, M.A., Ki-Young Park, Soo-Young Lee, Sejnowski, T.J.
Format: Conference Proceeding
Language:English
Subjects:
Biological neural networks
Brain
Image analysis
Image enhancement
Image motion analysis
Image processing
Independent component analysis
Laboratories
Learning algorithms
Nonlinear optics
Optical computing
Optical devices
Optical mixing
Optical rotation
Optical sensors
Probability density function
Statistical methods
Video sequences
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we describe the properties of independent components of optical flow of moving objects. Video sequences of objects seen by an observer moving at various angles, directions and distances are used to produce optical flow maps. These maps are then, recessed using independent component analysis, which yields filters that resemble the receptive fields of dorsal medial superior temporal cells of the primate brain. Contraction, expansion, rotation and translation receptive fields have been identified. Our results support Barlow's sensory coding theory and are in-line with other work on independent components of image and video intensities.
ISSN:0195-623X
2378-2226
DOI:10.1109/ISMVL.2000.848643