

浏览全部资源
扫码关注微信
西安建筑科技大学 建筑设备科学与工程学院,陕西 西安 710000
Received:08 November 2023,
Revised:2024-04-01,
Published:28 August 2025
移动端阅览
陈登峰,程静,赵蕾等.改进U‑Net模型的隧道掌子面图像语义分割研究[J].防灾减灾工程学报,2025,45(04):776-783.
CHEN Dengfeng,CHENG Jing,ZHAO Lei,et al.Semantic Segmentation of Tunnel Handheld Noodle Rock Mass Structure Images with Improved U‑Net Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(04):776-783.
陈登峰,程静,赵蕾等.改进U‑Net模型的隧道掌子面图像语义分割研究[J].防灾减灾工程学报,2025,45(04):776-783. DOI: 10.13409/j.cnki.jdpme.20231108005.
CHEN Dengfeng,CHENG Jing,ZHAO Lei,et al.Semantic Segmentation of Tunnel Handheld Noodle Rock Mass Structure Images with Improved U‑Net Model[J].Journal of Disaster Prevention and Mitigation Engineering,2025,45(04):776-783. DOI: 10.13409/j.cnki.jdpme.20231108005.
隧道掌子面岩体结构是判断岩土工程地质条件、制定施工和支护方案、预防塌方及涌水等事故的直观依据。将U‑Net模型应用于掌子面岩体结构图像分割与识别时,下采样过程中缩小图像尺寸会导致岩体部分细节信息丢失,上采样过程中将低层特征传递到高层的跳跃连接导致特征映射过大。因此,提出加入空洞空间卷积池化金字塔模块ASPP和卷积注意力模块CBAM的改进U‑Net模型。在U‑Net模型的跳跃连接过程中加ASPP,利用不同膨胀率的空洞卷积捕获不同尺度的上下文信息,融合不同感受野的信息,从而更全面的理解图像内容;U‑Net模型的下采样过程中加入CBAM,使网络模型更加关注有用的特征,从而增强特征的表达能力。实验结果表明,改进的网络模型相较于原始U‑Net模型分割和识别性能有显著提升,在某隧道工程掌子面岩体图像数据集上Precision达到93.04%,mIoU达到74.98%,mPA达到78.89%。
The structural characteristics of the rock mass exposed at the tunnel face provide a direct basis for assessing geotechnical conditions
formulating construction and support strategies
and mitigating risks of accidents such as collapses and water inrush. When applying the U‑Net model to the segmentation and recognition of tunnel face rock mass structure images
the downsampling process can lead to the loss of fine details in the rock mass
while the skip connections used during upsampling to transfer low-level features to higher levels may cause excessively large feature maps. To address these issues
an improved U-Net model is proposed by incorporating the Atrous Spatial Pyramid Pooling (ASPP) module and the Convolutional Block Attention Module (CBAM). Specifically
the ASPP is integrated into the skip connections of the U-Net model to capture multi-scale contextual information through atrous convolutions with varying dilation rates
enabling the fusion of features from diverse receptive fields for a more comprehensive understanding of image content. Concurrently
the CBAM is embedded into the downsampling process of the U-Net model to enhancing the network focus more on useful features
thereby enhancing the representation capability of the extracted features. Experimental results demonstrate that the improved network model significantly outperforms the original U-Net in both segmentation and recognition performance. Evaluated on a tunnel face rock mass image dataset from a specific engineering project
the improved model achieves a Precision of 93.04%
mean Intersection over Union (mIoU) of 74.98%
and a mean Pixel Accuracy (mPA) of 78.89%.
Pieter E S , Petr T , Petra T , et al . Characterizing the uppermost 100m structure of the San Jacinto fault zone southeast of Anza, California, through joint analysis of geological, topographic, seismic and resistivity data [J]. Geophysical Journal International , 2020 , 222 ( 1 ): 781 - 794 .
Jean-Claude B , Rigobert T , Joachim E , et al . Geological context mapping of Batouri Gold District (East Cameroon) from Remote sensing imagering, GIS processing and field works [J]. Journal of Geographic Information System , 2019 , 11 ( 6 ): 766 - 783 .
Geiger A , Lenz P , Urtasun R . Are we ready for autonomous driving? The KITTI vision benchmark suite [C]∥ Proceedings of IEEE Conference on Computer Vision & Pattern Recognition , New York : IEEE , 2012 , 3354 - 3361 .
Ohgushi T , Horiguchi K , Yamanaka M . Road Obstacle Detection Method Based on an Autoencoder With Semantic Segmentation [C]∥ Proceedings of the Asian Conference on Computer Vision . Springer , Cham , 2020 : 223 - 238 .
段杰 , 崔志明 , 沈艺 , 等 . 一种改进FCN的肝脏肿瘤CT图像分割方法 [J]. 图学学报 , 2020 , 41 ( 1 ): 100 - 107 .
Duan J , Cui Z M , Shen Y , et al . A CT image segmentation method for liver tumor by an improved FCN [J]. Journal of Graphics , 2020 , 41 ( 1 ): 100 - 107 . (in Chinese)
Otsu N . A threshold selection method from gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics , 1979 , 9 ( 1 ): 62 - 66 .
Yen J C , Chang F J , Chang S . A new criterion for automatic multilevel thresholding [J]. IEEE Transactions on Image Processing , 1995 , 4 ( 3 ): 370 - 378 .
Khani H , Hamdi H , Nghiem L , et al . An Improved Regional Segmentation for Probability Perturbation Method [C]∥ Proceedings of the 79th Eage Conference and Exhibition . Paris, France : [s.n.] , 2017 .
Wang H , Oliensis J . Generalizing edge detection to contour detection for image segmentation [J]. Computer Vision & Image Understanding , 2010 , 114 ( 7 ): 731 - 744 .
Achanta R , Shaji A , Smith K , et al . SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012 , 34 ( 11 ): 2274 - 2282 .
Zhu W , Shen Y . A region growing segmentation approach for MRI brain image processing [C]∥ Proceedings of IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification . Xiamen : [s.n.] , 2019 : 188 - 191 .
Lu S , Xin B , Deng N , et al . Investigation of cross-sectional image analysis method to determine the blending ratio of polyester/cotton yarn [J]. Journal of Microscopy , 2020 , 279 ( 1 ): 16 - 25 .
覃本学 , 沈疆海 , 马丙鹏 , 等 . 基于Debseg-Net的岩屑图像语义分割 [J]. 科学技术与工程 , 2022 , 22 ( 29 ): 12927 - 12935 ..
Qin B , Shen J , Ma B , et al . Semantic segmentation of rock debris image based on Debseg-Net [J]. Science Technology and Engineering , 2022 , 22 ( 29 ), 12927 - 12935 . (in Chinese) .
Wang X , Li Z , Huang Y , et al . Multimodal medical image segmentation using multi-scale context-aware network [J]. Neurocomputing , 2022 , 486 : 135 ‑ 146 .
Zou L , Zhang Z , Du H , et al . DA-IMRN: Dual-attention-guided interactive multi-scale residual network for hyperspectral image classification [J]. Remote Sensing , 2022 , 14 ( 3 ): 530 .
Ronneberger O , Fischer P , Brox T . U-net:convolutional networks for biomedical image segmentation [C]∥ Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention . Cham : Springer , 2015 , 9351 : 234 - 241 .
He X , Zhou Y , Zhao J , et al . Swin transformer embedding U‑Net for remote sensing image semantic segmentation [J]. IEEE Transactions on Geoscience and Remote Sensing , 2022 , 60 : 1 - 15 .
Woo S , Park J , Lee J Y . et al . CBAM: Convolutional block attention module [C]∥ Proceedings of the European conference on computer vision . Cham : Springer , 2018 , 11211 : 3 - 19 .
Chen L-C , Papandreou G , Kokkinos I , et al . DeepLab: Semantic Image Segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 40 ( 4 ): 834 - 848 .
Zhao H , Shi J , Qi X , et al . Pyramid Scene Parsing Network [C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , New York : IEEE Press , 2017 : 6230 - 6239 .
Chen L C , Zhu Y , Papandreou G , et al . Encoder-decoder with atrous separable convolution for semantic image segmentation [C]∥ Proceedings of the European conference on computer vision . Cham : Springer , 2018 : 801 ‑ 818 .
Long J , Shelhamer E , Darrell T . Fully convolutional networks for semantic segmentation [C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . New York : IEEE Press , 2015 : 3431 - 3440 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
苏公网安备32010202012147号