A System for Detecting and Locating Cracks in Dam Foundations on a Mobile Underwater Platform

In this paper, a system for detecting and locating cracks in dam foundations on underwater mobile platforms is proposed to address the technical problems of existing underwater dam foundation crack detection, such as serious image quality damage, incorrect extraction of crack information and inability to accurately locate cracks. The system uses an improved dark channel algorithm to defog the underwater images taken by the camera, combines the intelligent water droplet algorithm and the simulated annealing algorithm to extract the crack information from the defogged target images, and obtains the crack location by laser triangulation and conversion of the camera coordinate system. Experiments on real scenarios demonstrate that the method is able to reduce image quality impairment, extract valid crack information and return the location of cracks in the dam base, providing prior conditions for monitoring and repairing cracks in the dam base.