LSM-KinD: An Attention-Guided Low-LightEnhancement Model for Railway Fasteners

Abstract In railway fastener monitoring, poor lighting leads to issues like shadow distortion, overexposure, and loss of texture details, affecting system reliability and analysis accuracy. To address these, we propose the LSM-KinD model, which integrates the KinD architecture with SENet attention and multi-scale residual connections. The model uses an image decomposition network to separate reflection and illumination components, enhancing accuracy with multi-scale feature extraction and attention mechanisms. The illumination adjustment network applies residual blocks and channel attention to precisely control illumination, improving image quality. The image restoration network, based on U-Net and channel attention, optimizes the enhancement results. Experimental results show that LSM-KinD outperforms other algorithms, achieving PSNR and SSIM scores of 23.921 and 0.901 on the RAILF dataset. The model also improves detection accuracy, reaching a [email protected] of 84.9% in low-light environments, demonstrating its broad application potential in railway safety and system maintenance.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-16
DOI
https://doi.org/10.21203/rs.3.rs-8393482/v1
Primary Topic
Image Enhancement Techniques
Type
preprint

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

LSM-KinD: An Attention-Guided Low-LightEnhancement Model for Railway Fasteners

Xuehai Liu, Wupeng Deng, Changhao Chen, Yijie Cai et al.
2 links
Research Square
Image Enhancement Techniques
preprint

LSM-KinD: An Attention-Guided Low-LightEnhancement Model for Railway Fasteners

Xuehai Liu, Wupeng Deng, Changhao Chen, Yijie Cai, Feng Guo, Xiaojun Yang, Xing Dai, Jiannan Kang
preprint en

Abstract

Abstract In railway fastener monitoring, poor lighting leads to issues like shadow distortion, overexposure, and loss of texture details, affecting system reliability and analysis accuracy. To address these, we propose the LSM-KinD model, which integrates the KinD architecture with SENet attention and multi-scale residual connections. The model uses an image decomposition network to separate reflection and illumination components, enhancing accuracy with multi-scale feature extraction and attention mechanisms. The illumination adjustment network applies residual blocks and channel attention to precisely control illumination, improving image quality. The image restoration network, based on U-Net and channel attention, optimizes the enhancement results. Experimental results show that LSM-KinD outperforms other algorithms, achieving PSNR and SSIM scores of 23.921 and 0.901 on the RAILF dataset. The model also improves detection accuracy, reaching a [email protected] of 84.9% in low-light environments, demonstrating its broad application potential in railway safety and system maintenance.

Research Square
Groupe d’Étude de la Matière Condensée (FR), China Railway Group (China) (CN), China Railway Construction Machinery Research & Design Institute (CN), Hubei University of Technology (CN)
China Railway, Hubei University of Technology
Industry, innovation and infrastructure
Image Enhancement Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon