LMA-Net: Light-Guided Multi-Scale Attention for Robust Soil Crack Segmentation Under Complex Illumination
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Soil is highly susceptible to cracking under climatic factors such as rainfall and temperature, which degrades mechanical properties and durability and threatens the safety and service life of road infrastructure. Efficient and robust crack segmentation is therefore essential for infrastructure life-cycle performance. In real-world scenes, complex illumination conditions such as non-uniform lighting and shadows can substantially degrade segmentation accuracy. To address this problem, a light-guided multi-scale attention segmentation network (LMA-Net) is proposed for soil crack segmentation under complex illumination. The proposed model takes soil crack images captured under complex illumination conditions as input and outputs pixel-level crack segmentation maps. The network adopts a U-shaped encoder–decoder architecture and integrates an illumination-guided attention (IGA) module to suppress illumination interference, a multi-scale feature fusion (MSF) module to enhance crack representation across varying widths, and SE-ResBlocks to improve channel discriminability in deeper layers. In addition, a soil crack dataset was constructed under wetting–drying cycles and diverse complex illumination scenarios. A total of 164 raw images were acquired and preprocessed into 164 full-image inputs for model development, from which 1620 crack-containing patches were generated for training and validation. Experimental results show that LMA-Net achieves an IoU of 78.74% and an F1 score of 87.83% on the test set, outperforming the comparative segmentation networks by more than 4.64% in IoU and 3.07% in F1 score. Ablation studies further verify the effectiveness of the proposed modules, and qualitative evaluation on real-world engineering images demonstrates that LMA-Net has strong potential for soil crack segmentation under complex environmental conditions.
Fields of Study & Subjects
Infrastructure Maintenance and Monitoring
Advanced Neural Network Applications
Geotechnical and construction materials studies
Publication details
- Journal / source
- IEEE Access
- Volume
- 14
- Pages
- 48918–48933
- Publication date
- 1 January 2026
- Language
- EN