Design of an underground water leakage defect detection system using a lightweight image segmentation algorithm

Abstract With the continuous advancement of underground tunnel systems, the academic community has shown increasing concern about the hazards caused by water leakage. As one of the current research directions, instance segmentation algorithms still face several challenges in detecting water leakage defects in underground tunnels, such as insufficient accuracy in detecting small-sized targets and the large size of high-precision models, which is unfavorable for practical deployment. In view of this, this paper aims to design a lightweight instance segmentation model while maintaining high detection accuracy. This paper proposes an improved YOLOv11-seg algorithm based on the fusion of the local importance-based attention (LIA) mechanism, C3K2_CAS module and C3K2_CAFormer module for enhanced detection of underground water leakage defects in tunnel systems. This paper employs the Mosaic data augmentation technique for image enhancement, rendering image features more prominent and thus more favorable for machine learning. At the model level, we introduce an LIA mechanism, which aims to reduce computational complexity while preserving model performance, thereby enabling efficient information interaction. We further integrate the CAS_ViT and C3K2 modules into a unified C3K2_CAS module to replace the original C3K2 module—this design effectively captures fine-grained features while maintaining computational tractability. To further refine local features and enhance spatial information, we incorporate a C3K2_CAFormer module, which enhances local details such as edges while suppressing background noise. The optimized model achieves a Box_mAP50 of 80.3% and a Mask_mAP50 of 85.8% with only 3.2 million parameters. Compared to various mainstream models, it demonstrates the best overall performance, providing a low-cost and highly efficient solution for detecting water leakage defects in underground tunnels.