Causal graph-based video segmentation

Camille Couprie, Clement Farabet, Yann Lecun, Laurent Najman

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

Abstract

Among the different methods producing superpixel segmentations of an image, the graph-based approach of Felzenszwalb and Huttenlocher is broadly employed. One of its interesting properties is that the regions are computed in a greedy manner in quasi-linear time by using a minimum spanning tree. The algorithm may be trivially extended to video segmentation by considering a video as a 3D volume, however, this can not be the case for causal segmentation, when subsequent frames are unknown. In a framework exploiting minimum spanning trees all along, we propose an efficient video segmentation approach that computes temporally consistent pixels in a causal manner, filling the need for causal and real time applications.

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
PublisherIEEE Computer Society
Pages4249-4253
Number of pages5
ISBN (Print)9781479923410
DOIs
StatePublished - 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia
Duration: Sep 15 2013Sep 18 2013

Publication series

Name2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

Other

Other2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/TerritoryAustralia
CityMelbourne, VIC
Period9/15/139/18/13

Keywords

  • Optimization
  • graph-matching
  • superpixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Causal graph-based video segmentation'. Together they form a unique fingerprint.

Cite this