DocumentCode :
3138899
Title :
An adaptive multi-scale approach for estimating optical flow: computational theory and physiological implementation
Author :
Koch, Christof ; Wang, H. Taichi ; Battiti, Roberto ; Mathur, Bimal ; Ziomkowski, Chris
Author_Institution :
Comput. & Neural Syst. Program, California Inst. of Technol., Pasadena, CA, USA
fYear :
1991
fDate :
7-9 Oct 1991
Firstpage :
111
Lastpage :
122
Abstract :
The accuracy of optical flow estimation depends on the spatio-temporal discretization used in the computation. The authors propose an adaptive multiscale method, where the discretization scale is chosen locally according to an estimate of the relative error in the velocity measurements. They show that their coarse-to-fine method provides substantially better results of optical flow than conventional algorithms. The authors map this multiscale strategy onto their model of motion computation in primate area MT. The model consists of two stages: (1) local velocities are measured across multiple spatio-temporal channels, while (2) the optical flow field is computed by a network of direction-selective neurons at multiple spatial resolutions. Their model neurons show the same nonclassical receptive field properties as Allman´s type I MT neurons and lead to a novel interpretation of some aspect of the motion capture illusion
Keywords :
motion estimation; neurophysiology; visual perception; accuracy; adaptive multiscale method; coarse-to-fine method; direction-selective neurons; discretization scale; local velocities; motion capture illusion; multiple spatial resolutions; multiple spatio-temporal channels; optical flow; optical flow estimation; primate area MT; relative error; spatio-temporal discretization; velocity measurements; Adaptive optics; Area measurement; Computational modeling; Computer networks; Fluid flow measurement; Image motion analysis; Motion measurement; Neurons; Optical computing; Velocity measurement;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Visual Motion, 1991., Proceedings of the IEEE Workshop on
Conference_Location :
Princeton, NJ
Print_ISBN :
0-8186-2153-2
Type :
conf
DOI :
10.1109/WVM.1991.212780
Filename :
212780
Link To Document :
بازگشت