Multi-label learning of part detectors for occluded pedestrian detection

Despite recent progress of pedestrian detection, it remains a challenging problem to detect pedestrians that are partially occluded due to the uncertainty and diversity of partial occlusion patterns. Following a commonly used framework of handling partial occlusions by part detection, we propose a multi-label learning approach to jointly learn part detectors to capture partial occlusion patterns. The part detectors share a set of decision trees which are learned and combined via boosting to exploit part correlations and also reduce the computational cost of applying these part detectors for pedestrian detection. The learned decision trees capture the overall distribution of all the parts. When used as a pedestrian detector individually, our part detectors learned jointly show better performance than their counterparts learned separately in different occlusion situations. For occlusion handling, several methods are explored to integrate the part detectors learned by the proposed approach. Context is also exploited to further improve the performance. The proposed approach is applied to hand-crafted channel features and features learned by a deep convolutional neural network, respectively. Experiments on the Caltech and CUHK datasets show state-of-the-art performance of our approach for detecting occluded pedestrians, especially heavily occluded ones.