Handling occlusions with Franken-classifiers

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. © 2013 IEEE.Mathias M., Benenson R., Timofte R., Van Gool L., ''Handling occlusions with Franken-classifiers'', Proceedings 14th international conference on computer vision - ICCV 2013, pp. 1505-1512, December 3-6, 2013, Sydney, Australia.status: publishe