This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Handling Occlusions with Franken-classifiers

Markus Mathias, Rodrigo Benenson, Radu Timofte and Luc Van Gool
International Conference on Computer Vision (ICCV 2013)
Australia, December 2013


Detecting partially occluded pedestrians is challenging. A common practice to maximize detection quality is to train a set of occlusion-specific classifiers, each for a certain amount and type of occlusion. Since training classifiers is expensive, only a handful are typically trained. We show that by using many occlusion-specific classifiers, we outperform previous approaches on three pedestrian datasets; INRIA, ETH, and Caltech USA. We present a new approach to train such classifiers. By reusing computations among different training stages, 16 occlusion-specific classifiers can be trained at only one tenth the cost of one full training. We show that also test time cost grows sub-linearly.

Link to publisher's page
Download in pdf format
  author = {Markus Mathias and Rodrigo Benenson and Radu Timofte and Luc Van Gool},
  title = {Handling Occlusions with Franken-classifiers},
  booktitle = {International Conference on Computer Vision (ICCV 2013)},
  year = {2013},
  month = {December},
  keywords = {}