Relational Learning for Joint Head and Human Detection

TL;DR

This paper introduces JointDet, a novel neural network that jointly detects heads and humans, leveraging relational learning to improve accuracy and reduce false positives, especially in crowded scenes.

Contribution

The paper proposes a joint detection network with a head-body relationship module, achieving state-of-the-art results and providing new annotations and resources for the community.

Findings

JointDet outperforms existing methods on multiple benchmarks.

Relational learning reduces false positives and improves detection in crowds.

New annotations and code are publicly available.

Abstract

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.