Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Online Video Object Segmentation via Boundary-Constrained Low-Rank Sparse Representation
Chengdu Aeronaut Polytech, Dept Aeronaut Engn, Chengdu 610100, Sichuan, Peoples R China..
KTH, School of Industrial Engineering and Management (ITM), Production Engineering, Production Systems.ORCID iD: 0000-0001-8679-8049
Chengdu Aeronaut Polytech, Dept Aeronaut Engn, Chengdu 610100, Sichuan, Peoples R China..
Chengdu Aeronaut Polytech, Dept Aeronaut Engn, Chengdu 610100, Sichuan, Peoples R China..
Show others and affiliations
2019 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 53520-53533Article in journal (Refereed) Published
Abstract [en]

Graphcut-based algorithm is adopted in many video object segmentation systems because different terms can be probabilistically fused together in a framework. Constructing spatio-temporal coherences is an important stage in segmentation systems. However, many steps are involved when computing a key term with good discriminative power. If the cascade steps are adopted, the inaccurate output of the previous step will definitely affect the next step, leading to inaccurate segmentation. In this paper, a key term that is computed by a single framework referred to as boundary-constrained low-rank sparse representation (BCLRSR) is proposed to achieve the accurate segmentation. By treating the elements as linear combinations of dictionary templates, low-rank sparse optimization is adopted to achieve the spatio-temporal saliency. For adding the spatial information to the low-rank sparse model, a boundary constraint is adopted in the framework as a Laplacian regularization. A BCLRSR saliency is then obtained by the represented coefficients, which measure the similarity between the elements in the current frame and the ones in the dictionary. At last, the object is segmented by minimizing the energy function, which is formalized by the spatio-temporal coherences. The experiments on some public datasets show that our proposed algorithm outperforms the state-of-the-art methods.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2019. Vol. 7, p. 53520-53533
Keywords [en]
Energy minimization, Laplacian regularization, low rank sparse representation, video object segmentation
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-251722DOI: 10.1109/ACCESS.2019.2912760ISI: 000467030800001Scopus ID: 2-s2.0-85065496446OAI: oai:DiVA.org:kth-251722DiVA, id: diva2:1316625
Note

QC 20190520

Available from: 2019-05-20 Created: 2019-05-20 Last updated: 2019-05-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Wang, Lihui

Search in DiVA

By author/editor
Wang, Lihui
By organisation
Production Systems
In the same journal
IEEE Access
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 34 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf