Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene

doi:10.3390/app112411951

	Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene
	Liu, Kang 1; Zheng, Ying 1; Yang, Junyi 2; Bao, Hong 3; Zeng, Haoming 1
	2021-12-01
发表期刊	APPLIED SCIENCES-BASEL
卷号	11 期号:24 页码:19
摘要	For an automated driving system to be robust, it needs to recognize not only fixed signals such as traffic signs and traffic lights, but also gestures used by traffic police. With the aim to achieve this requirement, this paper proposes a new gesture recognition technology based on a graph convolutional network (GCN) according to an analysis of the characteristics of gestures used by Chinese traffic police. To begin, we used a spatial-temporal graph convolutional network (ST-GCN) as a base network while introducing the attention mechanism, which enhanced the effective features of gestures used by traffic police and balanced the information distribution of skeleton joints in the spatial dimension. Next, to solve the problem of the former graph structure only representing the physical structure of the human body, which cannot capture the potential effective features, this paper proposes an adaptive graph structure (AGS) model to explore the hidden feature between traffic police gesture nodes and a temporal attention mechanism (TAS) to extract features in the temporal dimension. In this paper, we established a traffic police gesture dataset, which contained 20,480 videos in total, and an ablation study was carried out to verify the effectiveness of the method we proposed. The experiment results show that the proposed method improves the accuracy of traffic police gesture recognition to a certain degree; the top-1 is 87.72%, and the top-3 is 95.26%. In addition, to validate the method's generalization ability, we also carried out an experiment on the Kinetics-Skeleton dataset in this paper; the results show that the proposed method is better than some of the existing action-recognition algorithms.
关键词	graph convolution network attention mechanism traffic police gesture recognition
DOI	10.3390/app112411951
收录类别	SCI
语种	英语
资助项目	Key Project of National Nature Science Foundation of China[61932012] ; Natural Science Foundation of Shanxi[201901D111467]
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
WOS类目	Chemistry, Multidisciplinary ; Engineering, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号	WOS:000735507600001
出版者	MDPI
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18362
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Bao, Hong
作者单位	1.China Univ Min & Technol Beijing, Sch Mech Elect & Informat Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China 3.Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Liu, Kang,Zheng, Ying,Yang, Junyi,et al. Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene[J]. APPLIED SCIENCES-BASEL,2021,11(24):19.
APA	Liu, Kang,Zheng, Ying,Yang, Junyi,Bao, Hong,&Zeng, Haoming.(2021).Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene.APPLIED SCIENCES-BASEL,11(24),19.
MLA	Liu, Kang,et al."Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene".APPLIED SCIENCES-BASEL 11.24(2021):19.