Skip to main content
placeholder image

Object detection by admissible region search

Journal Article


Abstract


  • Efficient Subwindow Search(ESS) is an effective method for object detection and localization, which adopts a scheme of branch-and-bound to find the global optimum of a quality function from all the possible subimages. Since the number of possible subimage is for an images with resolution, the time complexity of ESS ranges from to . In other words, ESS is equivalent to the exhaustive search in the worst case. In this paper, we propose a new method named Adimissible Region Search(ARS) for detecting and localizing the object with arbitrary shape in an image. Compared with the sliding window methods using ESS, ARS has two advantages: firstly, the time complexity is quadratic and stable so that it is more suitable to process large resolution images; secondly, the admissible region is adaptable to match the real shape of the target object and thus more suitable to represent the object. The experimental results on PASCAL VOC 2006 demonstrate that the proposed method is much faster than the ESS method on average.

UOW Authors


  •   Chen, Xiaoming (external author)
  •   An, Senjian (external author)
  •   Liu, Wanquan (external author)
  •   Li, Wanqing

Publication Date


  • 2011

Citation


  • Chen, X., An, S., Liu, W. & Li, W. (2011). Object detection by admissible region search. Lecture Notes in Computer Science, 7106 (N/A), 521-530. Perth, WA Object detection by admissible region search

Scopus Eid


  • 2-s2.0-83755196623

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/3800

Number Of Pages


  • 9

Start Page


  • 521

End Page


  • 530

Volume


  • 7106

Abstract


  • Efficient Subwindow Search(ESS) is an effective method for object detection and localization, which adopts a scheme of branch-and-bound to find the global optimum of a quality function from all the possible subimages. Since the number of possible subimage is for an images with resolution, the time complexity of ESS ranges from to . In other words, ESS is equivalent to the exhaustive search in the worst case. In this paper, we propose a new method named Adimissible Region Search(ARS) for detecting and localizing the object with arbitrary shape in an image. Compared with the sliding window methods using ESS, ARS has two advantages: firstly, the time complexity is quadratic and stable so that it is more suitable to process large resolution images; secondly, the admissible region is adaptable to match the real shape of the target object and thus more suitable to represent the object. The experimental results on PASCAL VOC 2006 demonstrate that the proposed method is much faster than the ESS method on average.

UOW Authors


  •   Chen, Xiaoming (external author)
  •   An, Senjian (external author)
  •   Liu, Wanquan (external author)
  •   Li, Wanqing

Publication Date


  • 2011

Citation


  • Chen, X., An, S., Liu, W. & Li, W. (2011). Object detection by admissible region search. Lecture Notes in Computer Science, 7106 (N/A), 521-530. Perth, WA Object detection by admissible region search

Scopus Eid


  • 2-s2.0-83755196623

Ro Metadata Url


  • http://ro.uow.edu.au/infopapers/3800

Number Of Pages


  • 9

Start Page


  • 521

End Page


  • 530

Volume


  • 7106