Exploiting Temporal Redundancy of Visual Structures for Video Compression

Author

Georgiadis, Georgios ; Soatto, Stefano

Author_Institution

Dept. of Comput. Sci., Univ. of California, Los Angeles, Los Angeles, CA, USA

fYear

2015

fDate

7-9 April 2015

Firstpage

445

Lastpage

445

Abstract

Summary form only given. We present a video coding system that partitions the scene into "visual structures" and a residual "background" layer. The system exploits the temporal redundancy of visual structures to compress video sequences. We construct a dictionary of track-templates, which correspond to a representation of visual structures. We subsequently choose a subset of the dictionary\´s elements to encode video frames using a Markov Random Field (MRF) formulation that places the track-templates in "depth" layers. Our video coding system offers an improvement over H.265/H.264 and other methods in a rate-distortion comparison.

Keywords

Markov processes; data compression; image sequences; redundancy; video coding; H.264 method; H.265 method; MOSEG; MRF formulation; Markov random field formulation; residual background layer; track-template dictionary; video coding system; video frame encoding; video sequence compression; visual structure temporal redundancy exploitation; Bit rate; Dictionaries; Redundancy; Tracking; Transform coding; Video coding; Visualization; video compression;

fLanguage

English

Publisher

ieee

Conference_Titel

Data Compression Conference (DCC), 2015

Conference_Location

Snowbird, UT

ISSN

1068-0314

Type

conf

DOI

10.1109/DCC.2015.30

Filename

7149308