Side Scan Sonar
Side-scan sonar (SSS) is an acoustic imaging technique used to map the seafloor, primarily employed by autonomous underwater vehicles (AUVs) for tasks like object detection, bathymetry reconstruction, and habitat classification. Current research focuses on improving automated analysis of SSS data using advanced machine learning models, including convolutional neural networks (CNNs) and vision transformers (ViTs), often incorporating techniques like knowledge distillation and active perception to enhance efficiency and accuracy. These advancements are significantly impacting underwater robotics, marine archaeology, and environmental monitoring by enabling more autonomous and efficient underwater surveys and improved interpretation of complex seafloor environments.
Papers
Synthetic Sonar Image Simulation with Various Seabed Conditions for Automatic Target Recognition
Jaejeong Shin, Shi Chang, Matthew Bays, Joshua Weaver, Tom Wettergren, Silvia Ferrari
Time and Cost-Efficient Bathymetric Mapping System using Sparse Point Cloud Generation and Automatic Object Detection
Andres Pulido, Ruoyao Qin, Antonio Diaz, Andrew Ortega, Peter Ifju, Jaejeong Shin