A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition

In skeleton-based human action recognition methods, human behaviours can be analysed through temporal and spatial changes in the human skeleton. Skeletons are not limited by clothing changes, lighting conditions, or complex backgrounds. This recognition method is robust and has aroused great interes...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yujian Jiang, Xue Yang, Jingyu Liu, Junming Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi-Wiley 2021
Materias:	Technology (General) T1-995 Science (General) Q1-390
Acceso en línea:	https://doaj.org/article/855d85fdcdfa4150a64cc6b93aea8a0f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:855d85fdcdfa4150a64cc6b93aea8a0f
record_format	dspace
spelling	oai:doaj.org-article:855d85fdcdfa4150a64cc6b93aea8a0f2021-11-15T01:20:12ZA Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition1939-012210.1155/2021/2290304https://doaj.org/article/855d85fdcdfa4150a64cc6b93aea8a0f2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/2290304https://doaj.org/toc/1939-0122In skeleton-based human action recognition methods, human behaviours can be analysed through temporal and spatial changes in the human skeleton. Skeletons are not limited by clothing changes, lighting conditions, or complex backgrounds. This recognition method is robust and has aroused great interest; however, many existing studies used deep-layer networks with large numbers of required parameters to improve the model performance and thus lost the advantage of less computation of skeleton data. It is difficult to deploy previously established models to real-life applications based on low-cost embedded devices. To obtain a model with fewer parameters and a higher accuracy, this study designed a lightweight frame-level joints adaptive graph convolutional network (FLAGCN) model to solve skeleton-based action recognition tasks. Compared with the classical 2s-AGCN model, the new model obtained a higher precision with 1/8 of the parameters and 1/9 of the floating-point operations (FLOPs). Our proposed network characterises three main improvements. First, a previous feature-fusion method replaces the multistream network and reduces the number of required parameters. Second, at the spatial level, two kinds of graph convolution methods capture different aspects of human action information. A frame-level graph convolution constructs a human topological structure for each data frame, whereas an adjacency graph convolution captures the characteristics of the adjacent joints. Third, the model proposed in this study hierarchically extracts different levels of action sequence features, making the model clear and easy to understand; further, it reduces the depth of the model and the number of parameters. A large number of experiments on the NTU RGB + D 60 and 120 data sets show that this method has the advantages of few required parameters, low computational costs, and fast speeds. It also has a simple structure and training process that make it easy to deploy in real-time recognition systems based on low-cost embedded devices.Yujian JiangXue YangJingyu LiuJunming ZhangHindawi-WileyarticleTechnology (General)T1-995Science (General)Q1-390ENSecurity and Communication Networks, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology (General) T1-995 Science (General) Q1-390
spellingShingle	Technology (General) T1-995 Science (General) Q1-390 Yujian Jiang Xue Yang Jingyu Liu Junming Zhang A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
description	In skeleton-based human action recognition methods, human behaviours can be analysed through temporal and spatial changes in the human skeleton. Skeletons are not limited by clothing changes, lighting conditions, or complex backgrounds. This recognition method is robust and has aroused great interest; however, many existing studies used deep-layer networks with large numbers of required parameters to improve the model performance and thus lost the advantage of less computation of skeleton data. It is difficult to deploy previously established models to real-life applications based on low-cost embedded devices. To obtain a model with fewer parameters and a higher accuracy, this study designed a lightweight frame-level joints adaptive graph convolutional network (FLAGCN) model to solve skeleton-based action recognition tasks. Compared with the classical 2s-AGCN model, the new model obtained a higher precision with 1/8 of the parameters and 1/9 of the floating-point operations (FLOPs). Our proposed network characterises three main improvements. First, a previous feature-fusion method replaces the multistream network and reduces the number of required parameters. Second, at the spatial level, two kinds of graph convolution methods capture different aspects of human action information. A frame-level graph convolution constructs a human topological structure for each data frame, whereas an adjacency graph convolution captures the characteristics of the adjacent joints. Third, the model proposed in this study hierarchically extracts different levels of action sequence features, making the model clear and easy to understand; further, it reduces the depth of the model and the number of parameters. A large number of experiments on the NTU RGB + D 60 and 120 data sets show that this method has the advantages of few required parameters, low computational costs, and fast speeds. It also has a simple structure and training process that make it easy to deploy in real-time recognition systems based on low-cost embedded devices.
format	article
author	Yujian Jiang Xue Yang Jingyu Liu Junming Zhang
author_facet	Yujian Jiang Xue Yang Jingyu Liu Junming Zhang
author_sort	Yujian Jiang
title	A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
title_short	A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
title_full	A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
title_fullStr	A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
title_full_unstemmed	A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition
title_sort	lightweight hierarchical model with frame-level joints adaptive graph convolution for skeleton-based action recognition
publisher	Hindawi-Wiley
publishDate	2021
url	https://doaj.org/article/855d85fdcdfa4150a64cc6b93aea8a0f
work_keys_str_mv	AT yujianjiang alightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT xueyang alightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT jingyuliu alightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT junmingzhang alightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT yujianjiang lightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT xueyang lightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT jingyuliu lightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition AT junmingzhang lightweighthierarchicalmodelwithframeleveljointsadaptivegraphconvolutionforskeletonbasedactionrecognition
_version_	1718428877085212672

A Lightweight Hierarchical Model with Frame-Level Joints Adaptive Graph Convolution for Skeleton-Based Action Recognition

Ejemplares similares