Segmentation-based coding of motion fields for video compression

Matthew S. Baker, Anthony J. Maeder

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

Abstract

In this paper, a motion field segmentation scheme for video compression is presented. A split- and-merge segmentation technique and linear regression are used to segment the field and an affine motion model is used to describe the movements of the regions. In the regression, a linearization of the displaced frame difference is minimize directly. The results are compared with block-based motion estimates and MPEG style coding.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsVasudev Bhaskaran, Frans Sijstermans, Sethuraman Panchanathan
Pages345-354
Number of pages10
DOIs
Publication statusPublished - 22 Mar 1996
Externally publishedYes
EventDigital Video Compression: Algorithms and Technologies 1996 - San Jose, CA, USA
Duration: 31 Jan 19962 Feb 1996

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume2668
ISSN (Print)0277-786X

Conference

ConferenceDigital Video Compression: Algorithms and Technologies 1996
CitySan Jose, CA, USA
Period31/01/962/02/96

Fingerprint Dive into the research topics of 'Segmentation-based coding of motion fields for video compression'. Together they form a unique fingerprint.

  • Cite this

    Baker, M. S., & Maeder, A. J. (1996). Segmentation-based coding of motion fields for video compression. In V. Bhaskaran, F. Sijstermans, & S. Panchanathan (Eds.), Proceedings of SPIE - The International Society for Optical Engineering (pp. 345-354). (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 2668). https://doi.org/10.1117/12.235429