A Deep Learning-based Artificial Intelligence Approach for the Automated Classification of Hydraulic Structures
DeepHyd project is funded by North Carolina Department of Transportation (NCDOT), aiming to reduce the labor work in monitoring the conditions of hydraulic structures(e.g. bridge piers, culverts, and scours). The measurement of these structures and estimation of their conditions are important in the asset management of NCDOT and public safety. Traditional approach either suffers difficulty in data acquisition in the unreachable site or needs much labor work in data processing. To facilitate this process, we have been developing a spatially explicit 3D modeling framework and a software package based on a cutting-edge artificial intelligence, deep learning, and state of art instruments in measurement including LiDAR, Drone, and unmanned boat sonar.
