A texture enhanced attention model for defect detection in thermal protection materials

Abstract Thermal protection materials are widely used in the aerospace field, where detecting internal defects is crucial for ensuring spacecraft structural integrity and safety in extreme temperature environments. Existing detection models struggle with these materials due to challenges like defect...

Full description

Saved in:
Bibliographic Details
Main Authors: Jialin Song, Zhaoba Wang, Kailiang Xue, Youxing Chen, Guodong Guo, Maozhen Li, Asoke K. Nandi
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-89376-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067182320353280
author Jialin Song
Zhaoba Wang
Kailiang Xue
Youxing Chen
Guodong Guo
Maozhen Li
Asoke K. Nandi
author_facet Jialin Song
Zhaoba Wang
Kailiang Xue
Youxing Chen
Guodong Guo
Maozhen Li
Asoke K. Nandi
author_sort Jialin Song
collection DOAJ
description Abstract Thermal protection materials are widely used in the aerospace field, where detecting internal defects is crucial for ensuring spacecraft structural integrity and safety in extreme temperature environments. Existing detection models struggle with these materials due to challenges like defect-background similarity, tiny size, and multi-scale characteristics. Besides, there is a lack of defect datasets in real-world scenarios. To address these issues, we first construct a thermal protection material digital radiographic (DR) image dataset (TPMDR-dataset), which contains 670 images from actual production and 6,269 defect instances annotated under expert guidance. And we propose an innovative texture-enhanced attention defect detection (TADD) model that enables accurate, efficient, and real-time defect detection. To implement the TADD model, we design a texture enhancement module that can enhance the concealed defect textures and features. Then we develop a non-local dual attention module to address the issue of severe feature loss in tiny defects. Moreover, we improve the model’s ability to detect multi-scale defects through a path aggregation network. The evaluation on the TPMDR-dataset and public dataset shows that the TADD model achieves a higher mean Average Precision (mAP) compared to other methods while maintaining 25 frames per second, exceeding the baseline model by 11.05%.
format Article
id doaj-art-3e409b9c07b248c0bd26ecd13f83dafe
institution DOAJ
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3e409b9c07b248c0bd26ecd13f83dafe2025-08-20T02:48:27ZengNature PortfolioScientific Reports2045-23222025-02-0115111710.1038/s41598-025-89376-4A texture enhanced attention model for defect detection in thermal protection materialsJialin Song0Zhaoba Wang1Kailiang Xue2Youxing Chen3Guodong Guo4Maozhen Li5Asoke K. Nandi6School of Information and Communication Engineering, North University of ChinaSchool of Information and Communication Engineering, North University of ChinaSchool of Information and Communication Engineering, North University of ChinaSchool of Information and Communication Engineering, North University of ChinaSchool of Information and Communication Engineering, North University of ChinaDepartment of Electronic and Electrical Engineering, Brunel University LondonDepartment of Electronic and Electrical Engineering, Brunel University LondonAbstract Thermal protection materials are widely used in the aerospace field, where detecting internal defects is crucial for ensuring spacecraft structural integrity and safety in extreme temperature environments. Existing detection models struggle with these materials due to challenges like defect-background similarity, tiny size, and multi-scale characteristics. Besides, there is a lack of defect datasets in real-world scenarios. To address these issues, we first construct a thermal protection material digital radiographic (DR) image dataset (TPMDR-dataset), which contains 670 images from actual production and 6,269 defect instances annotated under expert guidance. And we propose an innovative texture-enhanced attention defect detection (TADD) model that enables accurate, efficient, and real-time defect detection. To implement the TADD model, we design a texture enhancement module that can enhance the concealed defect textures and features. Then we develop a non-local dual attention module to address the issue of severe feature loss in tiny defects. Moreover, we improve the model’s ability to detect multi-scale defects through a path aggregation network. The evaluation on the TPMDR-dataset and public dataset shows that the TADD model achieves a higher mean Average Precision (mAP) compared to other methods while maintaining 25 frames per second, exceeding the baseline model by 11.05%.https://doi.org/10.1038/s41598-025-89376-4Defect detectionThermal protection materialConcealed object detectionTexture enhancementAttention mechanism
spellingShingle Jialin Song
Zhaoba Wang
Kailiang Xue
Youxing Chen
Guodong Guo
Maozhen Li
Asoke K. Nandi
A texture enhanced attention model for defect detection in thermal protection materials
Scientific Reports
Defect detection
Thermal protection material
Concealed object detection
Texture enhancement
Attention mechanism
title A texture enhanced attention model for defect detection in thermal protection materials
title_full A texture enhanced attention model for defect detection in thermal protection materials
title_fullStr A texture enhanced attention model for defect detection in thermal protection materials
title_full_unstemmed A texture enhanced attention model for defect detection in thermal protection materials
title_short A texture enhanced attention model for defect detection in thermal protection materials
title_sort texture enhanced attention model for defect detection in thermal protection materials
topic Defect detection
Thermal protection material
Concealed object detection
Texture enhancement
Attention mechanism
url https://doi.org/10.1038/s41598-025-89376-4
work_keys_str_mv AT jialinsong atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT zhaobawang atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT kailiangxue atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT youxingchen atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT guodongguo atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT maozhenli atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT asokeknandi atextureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT jialinsong textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT zhaobawang textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT kailiangxue textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT youxingchen textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT guodongguo textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT maozhenli textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials
AT asokeknandi textureenhancedattentionmodelfordefectdetectioninthermalprotectionmaterials