CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris

TL;DR

This paper introduces CANSURF, a new dataset and benchmark for detecting and tracking surface-level marine debris, specifically aluminum cans, using an autonomous surface vehicle's vision system.

Contribution

It provides the first open dataset targeting aluminum cans on water from a surface viewpoint and benchmarks multiple detection and tracking pipelines tailored for marine debris detection.

Findings

Training YOLOv11 on CANSURF improves detection performance 12x over generic datasets.

YOLOv11+ByteTrack offers the most stable multi-object tracking with fewer identity switches.

YOLOv11+SAHI increases recall for far-field cans, suitable for maximum detection in mission profiles.

Abstract

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.