Knowledge Commons of Institute of Automation,CAS
Relational Learning for Joint Head and Human Detection | |
Chi, Cheng1,2; Zhang, Shifeng1,3![]() ![]() ![]() ![]() | |
2020 | |
会议名称 | Association for the Advancement of Artificial Intelligence |
会议日期 | 2020-02 |
会议地点 | 美国纽约 |
摘要 | 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. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39044 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
作者单位 | 1.Aerospace Information Research Institute Chinese Academy of Sciences 2.Institute of Automation Chinese Academy of Sciences 3.University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chi, Cheng,Zhang, Shifeng,Xing, Junliang,et al. Relational Learning for Joint Head and Human Detection[C],2020. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论