Computer Vision – ECCV 2008

Volume 5303 of the series Lecture Notes in Computer Science pp 774-787

Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach

  • Qihui ZhuAffiliated withDepartment of Computer and Information Science, University of Pennsylvania
  • , Liming WangAffiliated withDepartment of Computer Science and Engineering, Fudan University
  • , Yang WuAffiliated withInstitue of Artificial Intelligence and Robotics, Xi’an Jiaotong University
  • , Jianbo ShiAffiliated withDepartment of Computer and Information Science, University of Pennsylvania

* Final gross prices may vary according to local VAT.

Get Access


We introduce a shape detection framework called Contour Context Selection for detecting objects in cluttered images using only one exemplar. Shape based detection is invariant to changes of object appearance, and can reason with geometrical abstraction of the object. Our approach uses salient contours as integral tokens for shape matching. We seek a maximal, holistic matching of shapes, which checks shape features from a large spatial extent, as well as long-range contextual relationships among object parts. This amounts to finding the correct figure/ground contour labeling, and optimal correspondences between control points on/around contours. This removes accidental alignments and does not hallucinate objects in background clutter, without negative training examples. We formulate this task as a set-to-set contour matching problem. Naive methods would require searching over ’exponentially’ many figure/ground contour labelings. We simplify this task by encoding the shape descriptor algebraically in a linear form of contour figure/ground variables. This allows us to use the reliable optimization technique of Linear Programming. We demonstrate our approach on the challenging task of detecting bottles, swans and other objects in cluttered images.