CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement

Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiayi Zhao, Alison Wun-Lam Yeung, Muhammad Ali, Songjiang Lai, Vincent To-Yee Ng
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10772194/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164942605385728
author Jiayi Zhao
Alison Wun-Lam Yeung
Muhammad Ali
Songjiang Lai
Vincent To-Yee Ng
author_facet Jiayi Zhao
Alison Wun-Lam Yeung
Muhammad Ali
Songjiang Lai
Vincent To-Yee Ng
author_sort Jiayi Zhao
collection DOAJ
description Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been developed in recent years, efficiently identifying small-scale rail defects has not yet been studied, especially for categories such as Dirt or Squat on rail surface. To address this challenge, this study utilizes Swin Transformer (SwinT) as baseline and incorporates the Convolutional Block Attention Module (CBAM) for enhancement. Our proposed method integrates CBAM successively within the swin transformer blocks, resulting in significant performance improvement in rail defect detection, particularly for categories with small instance sizes. The proposed framework is named CBAM-Enhanced Swin Transformer in Block Level (CBAM-SwinT-BL). Experiment and ablation study have proven the effectiveness of the framework. The proposed framework has a notable improvement in the accuracy of small size defects, such as dirt and dent categories in RIII dataset, with mAP-50 increasing by +23.0% and +38.3% respectively, and the squat category in MUET dataset also reaches +13.2% higher than the original model. Compares to the original SwinT, CBAM-SwinT-BL increase overall precision around +5% in the MUET dataset and +7% in the RIII dataset, reaching 69.1% and 88.1% respectively. Meanwhile, the additional module CBAM merely extend the model training speed by an average of +0.04s/iteration, which is acceptable compared to the significant improvement in system performance.
format Article
id doaj-art-86b05ba3325f4f2280cd86b06ab9bae2
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-86b05ba3325f4f2280cd86b06ab9bae22025-08-20T02:21:51ZengIEEEIEEE Access2169-35362024-01-011218199718200910.1109/ACCESS.2024.350998610772194CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM EnhancementJiayi Zhao0https://orcid.org/0009-0009-7208-0007Alison Wun-Lam Yeung1Muhammad Ali2Songjiang Lai3Vincent To-Yee Ng4Center for Advances in Reliability and Safety (CAiRS), New Territories, Hong Kong, ChinaCenter for Advances in Reliability and Safety (CAiRS), New Territories, Hong Kong, ChinaCenter for Advances in Reliability and Safety (CAiRS), New Territories, Hong Kong, ChinaCenter for Advances in Reliability and Safety (CAiRS), New Territories, Hong Kong, ChinaCenter for Advances in Reliability and Safety (CAiRS), New Territories, Hong Kong, ChinaUnder high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been developed in recent years, efficiently identifying small-scale rail defects has not yet been studied, especially for categories such as Dirt or Squat on rail surface. To address this challenge, this study utilizes Swin Transformer (SwinT) as baseline and incorporates the Convolutional Block Attention Module (CBAM) for enhancement. Our proposed method integrates CBAM successively within the swin transformer blocks, resulting in significant performance improvement in rail defect detection, particularly for categories with small instance sizes. The proposed framework is named CBAM-Enhanced Swin Transformer in Block Level (CBAM-SwinT-BL). Experiment and ablation study have proven the effectiveness of the framework. The proposed framework has a notable improvement in the accuracy of small size defects, such as dirt and dent categories in RIII dataset, with mAP-50 increasing by +23.0% and +38.3% respectively, and the squat category in MUET dataset also reaches +13.2% higher than the original model. Compares to the original SwinT, CBAM-SwinT-BL increase overall precision around +5% in the MUET dataset and +7% in the RIII dataset, reaching 69.1% and 88.1% respectively. Meanwhile, the additional module CBAM merely extend the model training speed by an average of +0.04s/iteration, which is acceptable compared to the significant improvement in system performance.https://ieeexplore.ieee.org/document/10772194/Object detectionsmall rail surface defectsSwin Transformerconvolutional block attention module (CBAM)attention mechanism
spellingShingle Jiayi Zhao
Alison Wun-Lam Yeung
Muhammad Ali
Songjiang Lai
Vincent To-Yee Ng
CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
IEEE Access
Object detection
small rail surface defects
Swin Transformer
convolutional block attention module (CBAM)
attention mechanism
title CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
title_full CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
title_fullStr CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
title_full_unstemmed CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
title_short CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer With Block Level CBAM Enhancement
title_sort cbam swint bl small rail surface defect detection method based on swin transformer with block level cbam enhancement
topic Object detection
small rail surface defects
Swin Transformer
convolutional block attention module (CBAM)
attention mechanism
url https://ieeexplore.ieee.org/document/10772194/
work_keys_str_mv AT jiayizhao cbamswintblsmallrailsurfacedefectdetectionmethodbasedonswintransformerwithblocklevelcbamenhancement
AT alisonwunlamyeung cbamswintblsmallrailsurfacedefectdetectionmethodbasedonswintransformerwithblocklevelcbamenhancement
AT muhammadali cbamswintblsmallrailsurfacedefectdetectionmethodbasedonswintransformerwithblocklevelcbamenhancement
AT songjianglai cbamswintblsmallrailsurfacedefectdetectionmethodbasedonswintransformerwithblocklevelcbamenhancement
AT vincenttoyeeng cbamswintblsmallrailsurfacedefectdetectionmethodbasedonswintransformerwithblocklevelcbamenhancement