Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector
Abstract Aircraft coating process has been an important part in manufacturing process of modern aviation products. For coating defect detection, the manual observation with naked eyes is usually utilized, which leads to low production efficiency. In this paper, the authors propose the improved YOLOv...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-04-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.13020 |
_version_ | 1797216877869531136 |
---|---|
author | Yongde Zhang Wei Wang Zhonghua Guo Yangchun Ji |
author_facet | Yongde Zhang Wei Wang Zhonghua Guo Yangchun Ji |
author_sort | Yongde Zhang |
collection | DOAJ |
description | Abstract Aircraft coating process has been an important part in manufacturing process of modern aviation products. For coating defect detection, the manual observation with naked eyes is usually utilized, which leads to low production efficiency. In this paper, the authors propose the improved YOLOv5‐OBB with the channel‐spatial attention block (CSAB), feature pyramid non‐local module (FPNM) and structured sparsity slimming criterion (SSSC). The CSAB can pay more attention to effective channel information features from the channel dimension and the target information area from the spatial dimension. The effective non‐local module called FPNM is proposed to further improve the detection accuracy. The authors utilize the oriented bounding boxes (OBB) to reduce redundant background information for coating defect detection. In addition, the SSSC is proposed to achieve network slimming and trade‐off between the efficiency and accuracy. The experimental results on several datasets demonstrate the effectiveness of the authors’ scheme, which achieves superior performance. |
first_indexed | 2024-04-24T11:52:57Z |
format | Article |
id | doaj.art-11e1e6b6b3b94147b6737d81ce2969e4 |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-04-24T11:52:57Z |
publishDate | 2024-04-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-11e1e6b6b3b94147b6737d81ce2969e42024-04-09T06:07:10ZengWileyIET Image Processing1751-96591751-96672024-04-011851213122810.1049/ipr2.13020Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detectorYongde Zhang0Wei Wang1Zhonghua Guo2Yangchun Ji3Key Laboratory of Advanced Manufacturing Technology of Zhejiang Province, College of Mechanical Engineering Zhejiang University Hangzhou ChinaAvic Xi'an Aircraft Industry Group Company Ltd. Xi'an ChinaAvic Xi'an Aircraft Industry Group Company Ltd. Xi'an ChinaAvic Xi'an Aircraft Industry Group Company Ltd. Xi'an ChinaAbstract Aircraft coating process has been an important part in manufacturing process of modern aviation products. For coating defect detection, the manual observation with naked eyes is usually utilized, which leads to low production efficiency. In this paper, the authors propose the improved YOLOv5‐OBB with the channel‐spatial attention block (CSAB), feature pyramid non‐local module (FPNM) and structured sparsity slimming criterion (SSSC). The CSAB can pay more attention to effective channel information features from the channel dimension and the target information area from the spatial dimension. The effective non‐local module called FPNM is proposed to further improve the detection accuracy. The authors utilize the oriented bounding boxes (OBB) to reduce redundant background information for coating defect detection. In addition, the SSSC is proposed to achieve network slimming and trade‐off between the efficiency and accuracy. The experimental results on several datasets demonstrate the effectiveness of the authors’ scheme, which achieves superior performance.https://doi.org/10.1049/ipr2.13020convolutional neural netsimage processingimage recognitionpattern recognitionquality controlvision defects |
spellingShingle | Yongde Zhang Wei Wang Zhonghua Guo Yangchun Ji Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector IET Image Processing convolutional neural nets image processing image recognition pattern recognition quality control vision defects |
title | Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector |
title_full | Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector |
title_fullStr | Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector |
title_full_unstemmed | Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector |
title_short | Research on oriented surface defect detection in the aircraft skin‐coating process based on an attention detector |
title_sort | research on oriented surface defect detection in the aircraft skin coating process based on an attention detector |
topic | convolutional neural nets image processing image recognition pattern recognition quality control vision defects |
url | https://doi.org/10.1049/ipr2.13020 |
work_keys_str_mv | AT yongdezhang researchonorientedsurfacedefectdetectionintheaircraftskincoatingprocessbasedonanattentiondetector AT weiwang researchonorientedsurfacedefectdetectionintheaircraftskincoatingprocessbasedonanattentiondetector AT zhonghuaguo researchonorientedsurfacedefectdetectionintheaircraftskincoatingprocessbasedonanattentiondetector AT yangchunji researchonorientedsurfacedefectdetectionintheaircraftskincoatingprocessbasedonanattentiondetector |