Xinbin Wu

Papers

Total Citations

H-Index

About

Xinbin Wu is a researcher at the forefront of applying deep learning and robotics to civil and hydraulic engineering challenges. Their primary research focuses on intelligent infrastructure inspection, particularly the automated detection and assessment of siltation and structural defects in water conveyance tunnels. Wu’s major contribution lies in pioneering the integration of underwater robots with advanced convolutional neural networks for real-time image recognition, enabling precise, non-destructive evaluation of submerged infrastructure. Their most-cited work, "Deep learning-based siltation image recognition of water conveyance tunnels using underwater robot" (2024, 10 citations), demonstrates a novel approach that significantly improves the accuracy and efficiency of sediment monitoring compared to traditional manual methods. This innovation has direct implications for reducing maintenance costs and preventing catastrophic failures in critical water supply systems. By bridging the gap between robotics, computer vision, and geotechnical engineering, Wu’s research offers a scalable, data-driven solution for aging infrastructure management. Their work is particularly notable for its practical deployment potential, setting a new standard for automated underwater inspection and contributing to the broader field of smart infrastructure and digital twin technologies.