Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.16774 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910225764712448 |
|---|---|
| author | Aljundi, Zaid Rahmatullah, Zahra F. Elemam, Mostafa Moosa, Abdullah |
| author_facet | Aljundi, Zaid Rahmatullah, Zahra F. Elemam, Mostafa Moosa, Abdullah |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16774 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris Aljundi, Zaid Rahmatullah, Zahra F. Elemam, Mostafa Moosa, Abdullah Computer Vision and Pattern Recognition Artificial Intelligence I.4.8; I.4.9; I.2; I.5 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. |
| title | CANSURF: An ASV-View Can Dataset and Benchmark for Detection and Tracking of Surface-Level Debris |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.4.8; I.4.9; I.2; I.5 |
| url | https://arxiv.org/abs/2605.16774 |