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
Pages4249-4253
Number of pages5
DOIs
StatePublished - 2013
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia
Duration: Sep 15 2013Sep 18 2013

Other

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

Fingerprint

Pixels

Keywords

  • graph-matching
  • Optimization
  • superpixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Couprie, C., Farabet, C., LeCun, Y., & Najman, L. (2013). Causal graph-based video segmentation. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 4249-4253). [6738875] https://doi.org/10.1109/ICIP.2013.6738875

Causal graph-based video segmentation. / Couprie, Camille; Farabet, Clement; LeCun, Yann; Najman, Laurent.

2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 4249-4253 6738875.

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

Couprie, C, Farabet, C, LeCun, Y & Najman, L 2013, Causal graph-based video segmentation. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738875, pp. 4249-4253, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 9/15/13. https://doi.org/10.1109/ICIP.2013.6738875
Couprie C, Farabet C, LeCun Y, Najman L. Causal graph-based video segmentation. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 4249-4253. 6738875 https://doi.org/10.1109/ICIP.2013.6738875
Couprie, Camille ; Farabet, Clement ; LeCun, Yann ; Najman, Laurent. / Causal graph-based video segmentation. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. pp. 4249-4253
@inproceedings{1755d83fbfdd497292d5413e6a03a64b,
title = "Causal graph-based video segmentation",
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.",
keywords = "graph-matching, Optimization, superpixels",
author = "Camille Couprie and Clement Farabet and Yann LeCun and Laurent Najman",
year = "2013",
doi = "10.1109/ICIP.2013.6738875",
language = "English (US)",
isbn = "9781479923410",
pages = "4249--4253",
booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

}

TY - GEN

T1 - Causal graph-based video segmentation

AU - Couprie, Camille

AU - Farabet, Clement

AU - LeCun, Yann

AU - Najman, Laurent

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - graph-matching

KW - Optimization

KW - superpixels

UR - http://www.scopus.com/inward/record.url?scp=84897749709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897749709&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738875

DO - 10.1109/ICIP.2013.6738875

M3 - Conference contribution

AN - SCOPUS:84897749709

SN - 9781479923410

SP - 4249

EP - 4253

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

ER -