Human posture recognition based on multiple features and rule learning

doi:10.1007/s13042-020-01138-y

CORC > 自动化研究所 > 中国科学院自动化研究所 > 融合创新中心 > 决策指挥与体系智能

	Human posture recognition based on multiple features and rule learning
	Ding, Weili 3; Hu, Bo 3; Liu, Han 2; Wang, Xinming 3; Huang, Xiangsheng 1
刊名	INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
	2020-06-02
页码	12
关键词	Human posture recognition Multiple features Rule learning
ISSN号	1868-8071
DOI	10.1007/s13042-020-01138-y
通讯作者	Liu, Han(liuh48@cardiff.ac.uk) ; Wang, Xinming(wang8297161@stumail.ysu.edu.cn)
英文摘要	The use of skeleton data for human posture recognition is a key research topic in the human-computer interaction field. To improve the accuracy of human posture recognition, a new algorithm based on multiple features and rule learning is proposed in this paper. Firstly, a 219-dimensional vector that includes angle features and distance features is defined. Specifically, the angle and distance features are defined in terms of the local relationship between joints and the global spatial location of joints. Then, during human posture classification, the rule learning method is used together with the Bagging and random subspace methods to create different samples and features for improved classification performance of sub-classifiers for different samples. Finally, the performance of our proposed algorithm is evaluated on four human posture datasets. The experimental results show that our algorithm can recognize many kinds of human postures effectively, and the results obtained by the rule-based learning method are of higher interpretability than those by traditional machine learning methods and CNNs.
资助项目	National Key R&D Program of China[2018YFB1308302] ; National Natural Science Foundation of China[61573356] ; Research and Practice Project of Innovation and Entrepreneurship Education Teaching Reform in Hebei Province[2017CXCY025]
WOS关键词	POSE
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER HEIDELBERG
WOS记录号	WOS:000537400100001
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China ; Research and Practice Project of Innovation and Entrepreneurship Education Teaching Reform in Hebei Province
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/39624]
专题	融合创新中心_决策指挥与体系智能
通讯作者	Liu, Han; Wang, Xinming
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Cardiff Univ, Sch Comp Sci & Informat, Queens Bldg 5, Cardiff CF24 3AA, Wales 3.Yanshan Univ, Inst Elect Engn, Dept Automat, Key Lab Intelligent Rehabil & Neromodulat Hebei P, 438 West Hebei Ave, Haigang Dist 066004, Qinghuangdao, Peoples R China
推荐引用方式 GB/T 7714	Ding, Weili,Hu, Bo,Liu, Han,et al. Human posture recognition based on multiple features and rule learning[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2020:12.
APA	Ding, Weili,Hu, Bo,Liu, Han,Wang, Xinming,&Huang, Xiangsheng.(2020).Human posture recognition based on multiple features and rule learning.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,12.
MLA	Ding, Weili,et al."Human posture recognition based on multiple features and rule learning".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2020):12.