CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris
For autonomous marine debris cleanup, this dataset fills a gap in surface-level small target detection, enabling reproducible evaluation and improved performance.
CANSURF introduces a new dataset of ~7.3k images of surface-level aluminum cans from an ASV viewpoint, augmented to ~57k images, and benchmarks detection/tracking pipelines. Training YOLOv11 on CANSURF improves detection performance 12x over generic datasets, with YOLOv11+SAHI best for maximizing recall in single-can pickup missions.
Surface-level marine debris remains a practical bottleneck for autonomous clean-up, where small, reflective targets (e.g., aluminum cans) must be detected at distance under glare, ripples, and partial submersion. This paper presents, an ASV vision system and a new surface-can dataset. The dataset comprises ~7.3k raw images extracted from videos and annotated with bounding boxes, expanded via ten augmentation types to ~57k training/validation images spanning diverse lighting and water states. A family of detector and detector-tracker pipelines tailored to surface operations were benchmarked. Training YOLOv11 on CANSURF boosts performance 12x over generic datasets, highlighting the dataset's value. Experiments show that YOLOv11+ByteTrack yields the most stable tracks (fewer identity switches) and stronger multi-object accuracy under, while YOLOv11+SAHI increases recall on far-field cans at the cost of lower precision in full-context inputs. Given the mission profile, single-can pickup with approach and grab, YOLOv11 + SAHI proves better for detecting the maximum number of cans. No prior open dataset targets aluminum cans on water from a surface-level viewpoint; this dataset fills this gap and supports reproducible evaluation.