The urban underground pipeline system is a critical infrastructure of cities, for which regular inspections for pipeline defects are required to ensure operational safety. However, defects in urban underground pipelines are often complicated by factors such as complex backgrounds, large-scale changes, diverse morphologies, and noise. To achieve efficient semantic segmentation of underground pipeline defects, an improved model, AME-DeepLabV3+, was proposed based on the DeepLabV3+ framework. The main improvements include the adaptive graph channel attention (AGCA) mechanism was introduced to optimize the feature representation in the channel dimension and enhance the model’s adaptability to complex scenarios. A multi-branch parallel convolution (MPConv) was designed to process low-level features, enhance edge details, and reduce interference from backgrounds and noise. An efficient selective feature fusion (ESFF) module was designed to achieve better feature fusion while reducing the number of parameters. Experimental results show that the improved DeepLabV3+ model increases mIoU by 4.76% and mPA by 1.69% compared to the baseline model, while maintaining real-time performance. Compared with other high-performance segmentation models such as SegFormer, certain advantages are also demonstrated by the proposed model.
ZhouQ, SituZ, FengW, et al. Deep learning, geometric characterization and hydrodynamic modeling for assessing sewer defect impacts on urban flooding: a case study in Guangzhou, China[J]. Journal of Environmental Management, 2024, 351: 119689.
[2]
HeJ, WangZ, YongZ, et al. An automatic defect detection and localization method using imaging geometric features for sewer pipes[J]. Measurement, 2025, 243: 116367.
[3]
LiM, FengX, WuZ, et al. Game engine-driven synthetic point cloud generation method for LiDAR-based defect detection in sewers[J]. Tunnelling and Underground Space Technology, 2025, 163: 106755.
[4]
LiM, FengX, LiuX. 3D point-cloud data corrosion model for predictive maintenance of concrete sewers[J]. Automation in Construction, 2024, 168: 105743.
[5]
TatiparthiS R, de CostaY G, WyllieD, et al. Real-time detection of sewer water levels and blockages using UHF-RFID sensors[J]. Water Research, 2025, 278: 123380.
[6]
GomezF, AlthoeferK, SeneviratneL D. An ultrasonic profiling method for sewer inspection[C]// IEEE International Conference on Robotics and Automation. New York: IEEE, 2004: 4858-4863.
YouXiaoling, CaiYongxiang, WangHui’ao, et al. FEDDR: a practical intelligent inspection system for underground drainage pipe-line defects[J]. Science Technology and Engineering, 2023, 23(7): 2932-2944.
[9]
SinhaS K, FieguthP W. Neuro-fuzzy network for the classification of buried pipe defects[J]. Automation in Construction, 2006, 15(1): 73-83.
[10]
HuynhP, RossR, MartchenkoA, et al.3D anomaly inspection system for sewer pipes using stereo vision and novel image processing[C]//2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA). New York: IEEE, 2016: 988-993.
[11]
MeijerD, LuimesR, KnobbeA, et al. Anomaly detection in urban drainage with stereovision[J]. Automation in Construction, 2022, 139: 104285.
CheLei, ZhangHongrui. A review of cloud image segmentation based on machine learning[J]. Science Technology and Engineering, 2025, 25(6): 2193-2206.
[14]
WangM Z, ChengC P. Semantic segmentation of sewer pipe defects using deep dilated convolutional neural network[C]// Proceedings of the International Symposium on Automation and Robotics in Construction. Banff: IAARC Publications, 2019: 586-594.
[15]
ZhouQ, SituZ, TengS, et al. Automatic sewer defect detection and severity quantification based on pixel-level semantic segmentation[J]. Tunnelling and Underground Space Technology, 2022, 123: 104403.
[16]
DangL M, WangH, LiY, et al. Lightweight pixel-level semantic segmentation and analysis for sewer defects using deep learning[J]. Construction and Building Materials, 2023, 371: 130792.
[17]
LiM, LiM, RenQ, et al. PipeTransUNet: CNN and Transformer fusion network for semantic segmentation and severity quantification of multiple sewer pipe defects[J]. Applied Soft Computing, 2024, 159: 111673.
[18]
DuC, WangK. Drainage pipeline defect detection system based on semantic segmentation[J]. Symmetry, 2024, 16(11): 1477.
[19]
ChenL C, PapandreouG, KokkinosI, 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.
[20]
XiangX, WangZ, ZhangJ, et al. AGCA: an adaptive graph channel attention module for steel surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-12.
[21]
WangQ, WuB, ZhuP, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and pattern Recognition. Seattle: IEEE, 2020: 11534-11542.
[22]
ChenL C, ZhuY, PapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 801-818.
[23]
CholletF. Xception: deep learning with depthwise separable convolutions[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1251-1258.
[24]
ChenY, ZhangC, ChenB, et al. Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases[J]. Computers in Biology and Medicine, 2024, 170: 107917.
[25]
LiuW, LuH, FuH, et al. Learning to upsample by learning to sample[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Paris: IEEE, 2023: 6027-6037.
[26]
HaurumJ B, MoeslundT B. Sewer-ML: a multi-label sewer defect classification dataset and benchmark[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13456-13467.
[27]
RonnebergerO, FischerP, BroxT. U-net: convolutional networks for biomedical image segmentation[C]// Medical Image Computing and Computer-assisted Intervention—MICCAI 2015: 18th International Conference. Munich: Springer International Publishing, 2015: 234-241.
[28]
ZhaoH, ShiJ, QiX, et al. Pyramid scene parsing network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 2881-2890.
[29]
WangJ, SunK, ChengT, et al. Deep high-resolution representation learning for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(10): 3349-3364.
[30]
XieE, WangW, YuZ, et al. SegFormer: simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.