liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Color Attributes for Object Detection
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
Universitat Autonoma de Barcelona, Spain.
Universitat Autonoma de Barcelona, Spain.
Universitat Autonoma de Barcelona, Spain.
Show others and affiliations
2012 (English)In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2012, IEEE , 2012, 3306-3313 p.Conference paper, Published paper (Refereed)
Abstract [en]

State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification, leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying importance of color and shape. In this paper we propose the use of color attributes as an explicit color representation for object detection. Color attributes are compact, computationally efficient, and when combined with traditional shape features provide state-of-the-art results for object detection. Our method is tested on the PASCAL VOC 2007 and 2009 datasets and results clearly show that our method improves over state-of-the-art techniques despite its simplicity. We also introduce a new dataset consisting of cartoon character images in which color plays a pivotal role. On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.

Place, publisher, year, edition, pages
IEEE , 2012. 3306-3313 p.
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-87580DOI: 10.1109/CVPR.2012.6248068ISI: 000309166203060ISBN: 978-1-4673-1227-1 (print)ISBN: 978-1-4673-1226-4 (print)OAI: oai:DiVA.org:liu-87580DiVA: diva2:600948
Conference
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Projects
CUAS
Available from: 2013-01-28 Created: 2013-01-18 Last updated: 2014-11-13

Open Access in DiVA

No full text

Other links

Publisher's full text

Authority records BETA

Khan, Fahad Shahbaz

Search in DiVA

By author/editor
Khan, Fahad Shahbaz
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 417 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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