Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature

Surface defect detection of an automobile wheel hub is important to the automobile industry because these defects directly affect the safety and appearance of automobiles. At present, surface defect detection networks based on convolutional neural network use many pooling layers when extracting feat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Chaowei Tang, Xinxin Feng, Haotian Wen, Xu Zhou, Yanqing Shao, Xiaoli Zhou, Baojin Huang, Yunzhen Li
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	high-resolution network optical flow semantic segmentation automobile wheel hub surface defect detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/21793a93a16947cbab79ae8476842677
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:21793a93a16947cbab79ae8476842677
record_format	dspace
spelling	oai:doaj.org-article:21793a93a16947cbab79ae84768426772021-11-25T16:30:06ZSemantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature10.3390/app1122105082076-3417https://doaj.org/article/21793a93a16947cbab79ae84768426772021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10508https://doaj.org/toc/2076-3417Surface defect detection of an automobile wheel hub is important to the automobile industry because these defects directly affect the safety and appearance of automobiles. At present, surface defect detection networks based on convolutional neural network use many pooling layers when extracting features, reducing the spatial resolution of features and preventing the accurate detection of the boundary of defects. On the basis of DeepLab v3+, we propose a semantic segmentation network for the surface defect detection of an automobile wheel hub. To solve the gridding effect of atrous convolution, the high-resolution network (HRNet) is used as the backbone network to extract high-resolution features, and the multi-scale features extracted by the Atrous Spatial Pyramid Pooling (ASPP) of DeepLab v3+ are superimposed. On the basis of the optical flow, we decouple the body and edge features of the defects to accurately detect the boundary of defects. Furthermore, in the upsampling process, a decoder can accurately obtain detection results by fusing the body, edge, and multi-scale features. We use supervised training to optimize these features. Experimental results on four defect datasets (i.e., wheels, magnetic tiles, fabrics, and welds) show that the proposed network has better F1 score, average precision, and intersection over union than SegNet, Unet, and DeepLab v3+, proving that the proposed network is effective for different defect detection scenarios.Chaowei TangXinxin FengHaotian WenXu ZhouYanqing ShaoXiaoli ZhouBaojin HuangYunzhen LiMDPI AGarticlehigh-resolution networkoptical flowsemantic segmentationautomobile wheel hubsurface defect detectionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10508, p 10508 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	high-resolution network optical flow semantic segmentation automobile wheel hub surface defect detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	high-resolution network optical flow semantic segmentation automobile wheel hub surface defect detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Chaowei Tang Xinxin Feng Haotian Wen Xu Zhou Yanqing Shao Xiaoli Zhou Baojin Huang Yunzhen Li Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
description	Surface defect detection of an automobile wheel hub is important to the automobile industry because these defects directly affect the safety and appearance of automobiles. At present, surface defect detection networks based on convolutional neural network use many pooling layers when extracting features, reducing the spatial resolution of features and preventing the accurate detection of the boundary of defects. On the basis of DeepLab v3+, we propose a semantic segmentation network for the surface defect detection of an automobile wheel hub. To solve the gridding effect of atrous convolution, the high-resolution network (HRNet) is used as the backbone network to extract high-resolution features, and the multi-scale features extracted by the Atrous Spatial Pyramid Pooling (ASPP) of DeepLab v3+ are superimposed. On the basis of the optical flow, we decouple the body and edge features of the defects to accurately detect the boundary of defects. Furthermore, in the upsampling process, a decoder can accurately obtain detection results by fusing the body, edge, and multi-scale features. We use supervised training to optimize these features. Experimental results on four defect datasets (i.e., wheels, magnetic tiles, fabrics, and welds) show that the proposed network has better F1 score, average precision, and intersection over union than SegNet, Unet, and DeepLab v3+, proving that the proposed network is effective for different defect detection scenarios.
format	article
author	Chaowei Tang Xinxin Feng Haotian Wen Xu Zhou Yanqing Shao Xiaoli Zhou Baojin Huang Yunzhen Li
author_facet	Chaowei Tang Xinxin Feng Haotian Wen Xu Zhou Yanqing Shao Xiaoli Zhou Baojin Huang Yunzhen Li
author_sort	Chaowei Tang
title	Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
title_short	Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
title_full	Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
title_fullStr	Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
title_full_unstemmed	Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature
title_sort	semantic segmentation network for surface defect detection of automobile wheel hub fusing high-resolution feature and multi-scale feature
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/21793a93a16947cbab79ae8476842677
work_keys_str_mv	AT chaoweitang semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT xinxinfeng semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT haotianwen semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT xuzhou semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT yanqingshao semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT xiaolizhou semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT baojinhuang semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature AT yunzhenli semanticsegmentationnetworkforsurfacedefectdetectionofautomobilewheelhubfusinghighresolutionfeatureandmultiscalefeature
_version_	1718413123071770624

Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature

Ejemplares similares