Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion
Abstract Intelligent recognition of assembly behaviors of workshop production personnel is crucial to improve production assembly efficiency and ensure production safety. This paper proposes a graph convolutional network model for assembly behavior recognition based on attention mechanism and multi-...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-05-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-11206-8 |
_version_ | 1811338726442270720 |
---|---|
author | Chengjun Chen Xicong Zhao Jinlei Wang Dongnian Li Yuanlin Guan Jun Hong |
author_facet | Chengjun Chen Xicong Zhao Jinlei Wang Dongnian Li Yuanlin Guan Jun Hong |
author_sort | Chengjun Chen |
collection | DOAJ |
description | Abstract Intelligent recognition of assembly behaviors of workshop production personnel is crucial to improve production assembly efficiency and ensure production safety. This paper proposes a graph convolutional network model for assembly behavior recognition based on attention mechanism and multi-scale feature fusion. The proposed model learns the potential relationship between assembly actions and assembly tools for recognizing assembly behaviors. Meanwhile, the introduction of an attention mechanism helps the network to focus on the key information in assembly behavior images. Besides, the multi-scale feature fusion module is introduced to enable the network to better extract image features at different scales. This paper constructs a data set containing 15 types of workshop production behaviors, and the proposed assembly behavior recognition model is tested on this data set. The experimental results show that the proposed model achieves good recognition results, with an average assembly recognition accuracy of 93.1%. |
first_indexed | 2024-04-13T18:16:15Z |
format | Article |
id | doaj.art-af43ff5221674015841d4c9252cafea6 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-13T18:16:15Z |
publishDate | 2022-05-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-af43ff5221674015841d4c9252cafea62022-12-22T02:35:41ZengNature PortfolioScientific Reports2045-23222022-05-0112111310.1038/s41598-022-11206-8Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusionChengjun Chen0Xicong Zhao1Jinlei Wang2Dongnian Li3Yuanlin Guan4Jun Hong5School of Mechanical and Automotive Engineering, Qingdao University of TechnologySchool of Mechanical and Automotive Engineering, Qingdao University of TechnologySchool of Mechanical and Automotive Engineering, Qingdao University of TechnologySchool of Mechanical and Automotive Engineering, Qingdao University of TechnologySchool of Mechanical and Automotive Engineering, Qingdao University of TechnologySchool of Mechanical Engineering, Xi’an Jiaotong UniversityAbstract Intelligent recognition of assembly behaviors of workshop production personnel is crucial to improve production assembly efficiency and ensure production safety. This paper proposes a graph convolutional network model for assembly behavior recognition based on attention mechanism and multi-scale feature fusion. The proposed model learns the potential relationship between assembly actions and assembly tools for recognizing assembly behaviors. Meanwhile, the introduction of an attention mechanism helps the network to focus on the key information in assembly behavior images. Besides, the multi-scale feature fusion module is introduced to enable the network to better extract image features at different scales. This paper constructs a data set containing 15 types of workshop production behaviors, and the proposed assembly behavior recognition model is tested on this data set. The experimental results show that the proposed model achieves good recognition results, with an average assembly recognition accuracy of 93.1%.https://doi.org/10.1038/s41598-022-11206-8 |
spellingShingle | Chengjun Chen Xicong Zhao Jinlei Wang Dongnian Li Yuanlin Guan Jun Hong Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion Scientific Reports |
title | Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion |
title_full | Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion |
title_fullStr | Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion |
title_full_unstemmed | Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion |
title_short | Dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi-scale feature fusion |
title_sort | dynamic graph convolutional network for assembly behavior recognition based on attention mechanism and multi scale feature fusion |
url | https://doi.org/10.1038/s41598-022-11206-8 |
work_keys_str_mv | AT chengjunchen dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion AT xicongzhao dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion AT jinleiwang dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion AT dongnianli dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion AT yuanlinguan dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion AT junhong dynamicgraphconvolutionalnetworkforassemblybehaviorrecognitionbasedonattentionmechanismandmultiscalefeaturefusion |