Handling Occlusions with Franken-Classifiers

Abstract

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.

Cite

Text

Mathias et al. "Handling Occlusions with Franken-Classifiers." International Conference on Computer Vision, 2013. doi:10.1109/ICCV.2013.190

Markdown

[Mathias et al. "Handling Occlusions with Franken-Classifiers." International Conference on Computer Vision, 2013.](https://mlanthology.org/iccv/2013/mathias2013iccv-handling/) doi:10.1109/ICCV.2013.190

BibTeX

@inproceedings{mathias2013iccv-handling,
  title     = {{Handling Occlusions with Franken-Classifiers}},
  author    = {Mathias, Markus and Benenson, Rodrigo and Timofte, Radu and Van Gool, Luc},
  booktitle = {International Conference on Computer Vision},
  year      = {2013},
  doi       = {10.1109/ICCV.2013.190},
  url       = {https://mlanthology.org/iccv/2013/mathias2013iccv-handling/}
}