Orthonormal Diffusion Decompositions of Images for Optical Flow Estimation

Sravan Kumar Naidu Gudivada, Adrian Gheorghe Bors

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an ortho-diffusion decomposition of graphs for estimating motion from image sequences. Orthonormal decompositions of the adjacency matrix representations of image data are alternated with diffusions and data subsampling in order to robustly represent image features using undirected graphs. Modified Gram-Schmidt with pivoting the columns algorithm is applied recursively for the orthonormal decompositions at various scales. This processing produces a set of ortho-diffusion bases and residual diffusion wavelets at each image representation scale. The optical flow is estimated using the similarity in the ortho-diffusion bases space extracted from regions of two different image frames.
Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns
Subtitle of host publication15th International Conference, CAIP 2013, York, UK, August 27-29, 2013, Proceedings, Part II
PublisherSpringer
Pages241-249
Number of pages9
Volume8048 LNCS
EditionPART 2
ISBN (Electronic)978-3-642-40246-3
ISBN (Print)978-3-642-40245-6
DOIs
Publication statusPublished - 2013
Event15th International Conference on Computer Analysis of Images and Patterns (CAIP 2013) - York, United Kingdom
Duration: 27 Aug 201329 Aug 2013

Publication series

NameLecture Notes in Computer Science
Volume8048
ISSN (Print)0302-9743

Conference

Conference15th International Conference on Computer Analysis of Images and Patterns (CAIP 2013)
Country/TerritoryUnited Kingdom
CityYork
Period27/08/1329/08/13

Cite this