Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels
mode - subway/metro, infrastructure - maintainance
Water leakage detection, Multispectral object detection, Multimodality feature fusion, One-stage, Anchor-free, Convolutional neural network
Water leakage detection has remained one of the high-priority research topics for metro tunnel inspection. Previous research mainly uses a single visible light camera as a sensor to detect the leakage regions in the image, which is extremely sensitive to inadequate illumination inside the tunnel. To robustly and accurately detect these water leakage defects in metro tunnels, we propose a novel detection method based on multispectral modality fusion that combines the advantages of visual-optical (VIS) and thermal infrared (IR) sensors. First, a multispectral data collection system is designed, and a four-dimensional water leakage dataset containing 1840 pictures is collected and labeled. Second, a simple and efficient one-stage anchor-free multispectral modality fusion network is proposed for water leakage detection. The proposed method consists of single-modality feature extraction and multimodality feature fusion based on a feature pyramid network (FPN). Finally, the VIS/IR single modality verification experiment proves that the VIS/IR based detector has unavoidable disadvantages in water leakage detection. The multispectral detection experiment proves that our proposed modality fusion detector achieves an approximately 3.35% lower average miss rate than the state-of-the-art method and can accurately and robustly detect leakage defects not affected by light conditions.
Permission to publish the abstract has been given by Elsevier, copyright remains with them.
Han, L., Chen, J., Li, H., Liu, G., Leng, B., Ahmed, A., & Zhang, Z. (2022). Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels. Automation in Construction, Vol. 140, 104345.
Automation in Construction Home Page: