Underground coal-rock image recognition using Swin-UNet with agent attention mechanism
SUN Chuanmeng
JIAO Bin
FU Yiyan
WU Yuxiang
WANG Yu
WANG Wenbo
LI Yong
Abstract：To address the challenges of coal-rock image segmentation under complex underground mining conditions—such as low illu-mination,high noise,and motion blur—this paper proposes an improved semantic segmentation model named Agent Swin-UNet,which integrates an Agent Attention mechanism into the Swin-UNet(Sliding Window Transformer U-Net)framework.The model adopts Swin Transformer as the backbone network,leveraging its hierarchical Window Multi-Head Self-Attention(W-MSA/SW-MSA)mechanism to establish long-range illumination dependencies,thereby alleviating detail loss in dark regions and degradation of local features.An Agent Attention Module is embedded into the skip connections between the encoder and decoder.This module introduces a triple-cooperative mechanism that employs agent tokens to realize an"aggregation-broadcast"style of feature interaction,reducing computational complex-ity from O(N2)to O(Nn)while preserving global semantic modeling capability and significantly improving computational efficiency.By incorporating spatially-aware bias,the model enhances its adaptability to noise distribution and effectively suppresses unstructured inter-ference,while the integration of depthwise separable convolution(DWC)strengthens local texture reconstruction,improving boundary de-lineation and fine-detail recovery.To mitigate the severe foreground-background imbalance inherent in coal-rock imagery,a composite loss function combining cross-entropy,Dice,and multi-scale structural similarity(MS-SSIM)losses is designed.This hybrid supervision optimizes the training process from multiple perspectives—classification consistency,regional overlap,and structural similarity—enhan-cing semantic coherence and boundary completeness under class-imbalance conditions.Experiments on the Shaanxi-Shanxi-Hebei Struc-tural Coal Dataset demonstrate that Agent Swin-UNet achieves 91.26%mIoU and 88.81%mPA on the standard test set,outperforming Segmenter,DeepLabv3,and the baseline Swin-UNet.Under noise interference with an intensity of 0.05,its mIoU remains 84.14%,indic-ating excellent noise robustness.Ablation studies further confirm that the Agent Attention Module is the principal source of performance improvement,particularly in high-noise environments(>0.05).The proposed method provides a robust and efficient solution for rapid coal-rock segmentation and intelligent excavation in complex underground environments.
Keywords：intelligent coal minecoal-rock recognitionimage recognitionagent attentionsemantic segmentation
Publication Date：2025-11-30
Online Publishing Date：2025-12-15(First online date of this platform, not the publication date of the document)
Pages：14( 158-171 )