期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 23, 期 -, 页码 3085-3097出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2020.3020691
关键词
Detectors; Semantics; Feature extraction; Proposals; Object detection; Task analysis; Training; Attribute-aware; non-maximum suppression (nms); pedestrian detection
资金
- National Natural Science Foundation of China [61831015]
The study introduces an attribute-aware pedestrian detector that models people's semantic attributes explicitly and utilizes attribute-feature-based Non-Maximum Suppression to improve pedestrian detection accuracy in dense environments. Additionally, an enhanced ground truth target is designed to alleviate the class imbalance issue during training.
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 occlusions, 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, an enhanced ground truth target is designed to alleviate the difficulties caused by the attribute configuration, and to ease the class imbalance issue during training. Finally, we evaluate our proposed attribute-aware pedestrian detector on three benchmark datasets including CityPerson, CrowdHuman, and EuroCityPerson, and achieves the state-of-the-art results.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据