Video segmentation with joint object and trajectory labeling

Michael Ying Yang, Bodo Rosenhahn

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Citations (Scopus)

Abstract

Unsupervised video object segmentation is a challenging problem because it involves a large amount of data and object appearance may significantly change over time. In this paper, we propose a bottom-up approach for the combination of object segmentation and motion segmentation using a novel graphical model, which is formulated as inference in a conditional random field (CRF) model. This model combines object labeling and trajectory clustering in a unified probabilistic framework. The CRF contains binary variables representing the class labels of image pixels as well as binary variables indicating the correctness of trajectory clustering, which integrates dense local interaction and sparse global constraint. An optimization scheme based on a coordinate ascent style procedure is proposed to solve the inference problem. We evaluate our proposed framework by comparing it to other video and motion segmentation algorithms. Our method achieves improved performance on state-of-the-art benchmark datasets.

Original languageEnglish
Title of host publicationIEEE Winter Conference on Applications of Computer Vision, WACV 2014
Place of PublicationSteamboat Springs
PublisherIEEE Computer Society
Pages831-838
Number of pages8
ISBN (Print)9781479949854
DOIs
Publication statusPublished - 23 Jun 2014
Externally publishedYes
EventIEEE Winter Conference on Applications of Computer Vision, WACV 2014 - Steamboat Springs, United States
Duration: 24 Mar 201426 Mar 2014
http://wacv14.wacv.net/

Publication series

Name2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision, WACV 2014
Abbreviated titleWACV 2014
CountryUnited States
CitySteamboat Springs
Period24/03/1426/03/14
Internet address

Fingerprint Dive into the research topics of 'Video segmentation with joint object and trajectory labeling'. Together they form a unique fingerprint.

Cite this