A cost-effective autonomous underwater system for small size object detection

According to US National Oceanic and Atmospheric Administration (NOAA), we have only explored five percent of our world ocean. Among the ocean exploration tasks, underwater object detection is a multidisciplinary challenge that extends beyond engineering into fields such as oceanography, marine biology, and environmental science. Scientifically, it involves understanding the complex interactions between sound waves, light, and water, as well as the navigation dynamics within marine environments. The underwater environment presents unique physical challenges for object detection due to factors like light attenuation, turbidity, and the variability of acoustic propagation. This paper introduces a cost-effective autonomous underwater prototype for real-time detection, and localization of small underwater objects (e.g., archaeological artifacts, parts of infrastructures, wreckage debris, but also life forms like fishes, corals etc.) in shallow waters. The system combines object identification with autonomous navigation capabilities. It consists of an autonomous underwater vehicle equipped with sensors, cameras, and localization tools, as well as a ground control station for monitoring and intervention. In particular, we focus on a case study about detecting and reporting the locations of unexploded ordnance materials, contributing to the monitoring of underwater hazards in conflict-affected regions. Key contributions include the integration of a cost-effective autonomous remotely operated vehicle with sensors and software for real-time detection and localization of small underwater objects, as well as an annotated dataset of UXO images, usable as a benchmark.