PCN: Part and Context Information for Pedestrian Detection with CNNs
This work addresses occlusion handling in pedestrian detection, which is a critical problem for applications like autonomous driving, but it appears incremental as it builds on existing CNN-based methods with specific enhancements.
The paper tackled pedestrian detection under occlusion by proposing a Part and Context Network (PCN) that uses body parts and context information in separate branches, resulting in a lower miss rate and better localization accuracy, especially for occluded pedestrians, as validated on Caltech and INRIA datasets.
Pedestrian detection has achieved great improvements in recent years, while complex occlusion handling is still one of the most important problems. To take advantage of the body parts and context information for pedestrian detection, we propose the part and context network (PCN) in this work. PCN specially utilizes two branches which detect the pedestrians through body parts semantic and context information, respectively. In the Part Branch, the semantic information of body parts can communicate with each other via recurrent neural networks. In the Context Branch, we adopt a local competition mechanism for adaptive context scale selection. By combining the outputs of all branches, we develop a strong complementary pedestrian detector with a lower miss rate and better localization accuracy, especially for occlusion pedestrian. Comprehensive evaluations on two challenging pedestrian detection datasets (i.e. Caltech and INRIA) well demonstrated the effectiveness of the proposed PCN.