SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles
A lack of publicly available, high-quality underwater obstacle perception datasets for autonomous surface vehicles (ASVs) operating in complex hydrodynamic environments hinders progress in marine autonomous navigation. Method: This work introduces ASV-Underwater—the first open-source, multimodal underwater obstacle dataset specifically designed for ASVs. Collected over four years, it encompasses diverse targets, turbid water conditions, low-light scenarios, and dynamic occlusions, with temporally synchronized optical and acoustic imagery. All data are annotated with ego-centric, fine-grained pixel-level and bounding-box labels, and formatted to comply with standard detection frameworks (e.g., YOLOv8, Faster R-CNN). Contribution/Results: Experiments demonstrate that models trained on ASV-Underwater achieve significantly improved robustness in underwater obstacle detection and classification, effectively addressing a critical data gap in maritime perception research.