Relational Learning for Joint Head and Human Detection
This addresses detection issues in crowded scenes for computer vision applications, but is incremental as it builds on existing deep learning methods.
The paper tackles the problem of separate head and human detection leading to false positives and performance drops in crowds by proposing JointDet, a joint detection network with relational learning, achieving state-of-the-art performance on CrowdHuman, CityPersons, and Caltech-USA benchmarks.
Head and human detection have been rapidly improved with the development of deep convolutional neural networks. However, these two tasks are often studied separately without considering their inherent correlation, leading to that 1) head detection is often trapped in more false positives, and 2) the performance of human detector frequently drops dramatically in crowd scenes. To handle these two issues, we present a novel joint head and human detection network, namely JointDet, which effectively detects head and human body simultaneously. Moreover, we design a head-body relationship discriminating module to perform relational learning between heads and human bodies, and leverage this learned relationship to regain the suppressed human detections and reduce head false positives. To verify the effectiveness of the proposed method, we annotate head bounding boxes of the CityPersons and Caltech-USA datasets, and conduct extensive experiments on the CrowdHuman, CityPersons and Caltech-USA datasets. As a consequence, the proposed JointDet detector achieves state-of-the-art performance on these three benchmarks. To facilitate further studies on the head and human detection problem, all new annotations, source codes and trained models will be public.