Occlusion Patterns for Object Class Detection


Conference Paper


Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion re- mains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of meth- ods that treat occlusion as just another source of noise – instead, we include the occluder itself into the modelling, by mining distinctive, reoccurring occlusion patterns from annotated training data. These patterns are then used as training data for dedicated detectors of varying sophistica- tion. In particular, we evaluate and compare models that range from standard object class detectors to hierarchical, part-based representations of occluder/occludee pairs. In an extensive evaluation we derive insights that can aid fur- ther developments in tackling the occlusion challenge.

Author(s): Bojan Pepik and Michael Stark and Peter Gehler and Bernt Schiele
Book Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Year: 2013
Month: June

Department(s): Perceiving Systems
Research Project(s): 3D Recognition
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Portland, OR
Attachments: pdf


  title = {Occlusion Patterns for Object Class Detection},
  author = {Pepik, Bojan and Stark, Michael and Gehler, Peter and Schiele, Bernt},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
  address = {Portland, OR},
  month = jun,
  year = {2013},
  month_numeric = {6}