Shape constrained figure-ground segmentation and tracking

Zhaozheng Yin, Robert T. Collins

Research output: Chapter in Book/Report/Conference proceedingConference contribution

40 Scopus citations


Global shape information is an effective top-down complement to bottom-up figure-ground segmentation as well as a useful constraint to avoid drift during adaptive tracking. We propose a novel method to embed global shape information into local graph links in a Conditional Random Field (CRF) framework. Given object shapes from several key frames, we automatically collect a shape dataset onthe- fly and perform statistical analysis to build a collection of deformable shape templates representing global object shape. In new frames, simulated annealing and local voting align the deformable template with the image to yield a global shape probability map. The global shape probability is combined with a region-based probability of object boundary map and the pixel-level intensity gradient to determine each link cost in the graph. The CRF energy is minimized by min-cut, followed by Random Walk on the uncertain boundary region to get a soft segmentation result. Experiments on both medical and natural images with deformable object shapes are demonstrated.

Original languageEnglish (US)
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PublisherIEEE Computer Society
Number of pages8
ISBN (Print)9781424439935
StatePublished - 2009
Event2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States
Duration: Jun 20 2009Jun 25 2009

Publication series

Name2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009


Conference2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Country/TerritoryUnited States
CityMiami, FL

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering


Dive into the research topics of 'Shape constrained figure-ground segmentation and tracking'. Together they form a unique fingerprint.

Cite this