Sonar is one of the main tools used for marine research, target detection and localization, offshore infrastructure inspection, and search-and-rescue missions because sonar systems can reveal features that are difficult to detect with conventional cameras. UM’s Shahriar Negahdaripour will use machine learning to better understand how sonar systems create images.
His goal is to help researchers build more accurate three-dimensional models of underwater environments from two-dimensional sonar images. “Building accurate representations of underwater environments … could enable the creation of digital twins, virtual models that mirror real-world underwater environments," says Negahdaripour. "These tools could help researchers monitor marine ecosystems and inspect offshore infrastructure, turning the survey data into dynamic, living replicas of the ocean.”
View Related Expert Profiles: Go to Source
