English

Attribute-aware Pedestrian Detection in a Crowd

Computer Vision and Pattern Recognition 2019-12-24 v2

Abstract

Pedestrian detection is an initial step to perform outdoor scene analysis, which plays an essential role in many real-world applications. Although having enjoyed the merits of deep learning frameworks from the generic object detectors, pedestrian detection is still a very challenging task due to heavy occlusion and highly crowded group. Generally, the conventional detectors are unable to differentiate individuals from each other effectively under such a dense environment. To tackle this critical problem, we propose an attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion. Besides the typical semantic features, center position, target's scale and offset, we introduce a pedestrian-oriented attribute feature to encode the high-level semantic differences among the crowd. Moreover, a novel attribute-feature-based Non-Maximum Suppression~(NMS) is proposed to distinguish the person from a highly overlapped group by adaptively rejecting the false-positive results in a very crowd settings. Furthermore, a novel ground truth target is designed to alleviate the difficulties caused by the attribute configuration and extremely class imbalance issues during training. Finally, we evaluate our proposed attribute-aware pedestrian detector on two benchmark datasets including CityPersons and CrowdHuman. The experimental results show that our approach outperforms state-of-the-art methods at a large margin on pedestrian detection.

Keywords

Cite

@article{arxiv.1910.09188,
  title  = {Attribute-aware Pedestrian Detection in a Crowd},
  author = {Jialiang Zhang and Lixiang Lin and Yang Li and Yun-chen Chen and Jianke Zhu and Yao Hu and Steven C. H. Hoi},
  journal= {arXiv preprint arXiv:1910.09188},
  year   = {2019}
}
R2 v1 2026-06-23T11:49:29.901Z