Learning to Integrate Occlusion-Specific Detectors for Heavily Occluded Pedestrian Detection

It is a challenging problem to detect partially occluded pedestrians due to the diversity of occlusion patterns. Although training occlusionspecific detectors can help handle various partial occlusions, it is a nontrivial problem to integrate these detectors properly. A direct combination of all occlusion-specific detectors can be affected by unreliable detectors and usually does not favor heavily occluded pedestrian examples, which can only be recognized by few detectors. Instead of combining all occlusion-specific detectors into a generic detector for all occlusions, we categorize occlusions based on how pedestrian examples are occluded into K groups. Each occlusion group selects its own occlusion-specific detectors and fuses them linearly to obtain a classifer. An L1-norm linear support vector machine (SVM) is adopted to select and fuse occlusionspecific detectors for the K classifiers simultaneously. Thanks to the L1norm linear SVM, unreliable and irrelevant detectors are removed for each group. Experiments on the Caltech dataset show promising performance of our approach for detecting heavily occluded pedestrians.