张新峰,范 铭,曹哲宇,杨文强,于海洋,张海兵,李 斌.基于几何统计的人体姿态语义描述方法[J].电子测量与仪器学报,2023,37(8):52-59 |
基于几何统计的人体姿态语义描述方法 |
Human posture semantic description method based on geometric statistics |
|
DOI: |
中文关键词: 姿态识别 语义描述 智能监控 关键点检测 关键点集合 几何统计 |
英文关键词:gesture recognition semantic description intelligent monitoring key point detection key point set geometric statistics |
基金项目:国家自然科学基金(61801417,61972335)项目资助 |
|
Author | Institution |
Zhang Xinfeng | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Fan Ming | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Cao Zheyu | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Yang Wenqiang | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Yu Haiyang | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Zhang Haibing | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
Li Bin | 1. College of Information Engineering (College of Artificial Intelligence), Yangzhou University,2. Jiangsu Province Engineering Research Center of Knowledge Management and Intelligent Service |
|
摘要点击次数: 973 |
全文下载次数: 597 |
中文摘要: |
准确高效地对人体姿态进行语义描述是识别人类行为的重要部分,也是快速了解个体状态以及发生事件的关键。 近年
来,人体关键点检测技术获得了长足的发展,然而针对人体姿态语义描述的研究并未引起足够重视。 为此,本文提出了一种基
于几何统计的人体姿态语义描述方法。 首先将获得的人体关键点划分为若干集合,然后提取每个关键点集合的几何分布特征
用于描述人体姿态,最后采用层次策略判断人体姿态的语义。 该方法采用了集合的思想来提高识别人体姿态的鲁棒性。 在不
同真实场景数据集上的实验结果表明,所提方法在简单和复杂单人姿态的 IFD 和 PASCAL 数据集上识别人体姿态的平均准确
率分别达到了 90. 8%和 77. 1%,对于复杂多人姿态的 MPII 数据集准确率为 77. 2%,均优于对比方法,可见所提方法在关键点缺
失等情况下依然能够实现较准确的人体姿态语义描述。 |
英文摘要: |
Accurate and efficient semantic description of human posture is integral to human behavior recognition. It is also a key to
quickly understanding individual states and events. In recent years, human key point detection technology has gained significant
development. However, the research on the semantic description of the human pose has not attracted enough attention. To this end, we
propose a geometric statistics-based semantic description method for human posture. Firstly, the obtained human key points are divided
into several sets. Then, the geometric distribution characteristics of each key point set are calculated to describe the human posture.
Finally, the semantics of the human pose is judged using a hierarchical strategy. This method employs the idea of the set to improve the
robustness of recognizing human posture. The experimental results on multiple real scene datasets show that the proposed method attains
an average accuracy of 90. 8% and 77. 1% for identifying human pose on the IFD and PASCAL datasets for simple and complex singleperson pose, respectively, and 77. 2% on the MPII dataset for the complicated multi-person pose, which are better than the performance
of compared approaches. In conclusion, the proposed method can achieve more accurate human pose semantic descriptions despite the
absence of some key points. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|