Detection of Submerged Targets Beyond Eyes' Observation Using Satellite Lidar and Multispectral Data

Abstract Detecting submerged targets in shallow waters from satellite platforms remains a challenge, as the optical spectral information of targets is significantly distorted by the absorption and scattering effects of the water column. In this study, we propose a new framework as the bathymetry‐informed target extraction, which integrates the spaceborne lidar data and multispectral imagery. By using lidar assisted Satellite‐Derived Bathymetry model, we convert the complex multispectral information into relative depth data. Through this transformation, the challenging issue of distorted color domain image segmentation is converted into the task of depth anomaly detection. The method is validated on submerged artificial stone weirs and breakwaters in typical open ocean and coastal waters, which indicates significant improvements in target detection rate and reliability compared to direct color‐based methods. This approach promises large‐scale surveys of submerged targets in shallow waters, offering an alternative solution to on‐site surveys such as shipborne sonars.