SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915721219407872 |
|---|---|
| author | Jeong, Mingi Chadda, Arihant Ren, Ziang Zhao, Luyang Liu, Haowen Roznere, Monika Zhang, Aiwei Jiang, Yitao Achong, Sabriel Lensgraf, Samuel Li, Alberto Quattrini |
| author_facet | Jeong, Mingi Chadda, Arihant Ren, Ziang Zhao, Luyang Liu, Haowen Roznere, Monika Zhang, Aiwei Jiang, Yitao Achong, Sabriel Lensgraf, Samuel Li, Alberto Quattrini |
| contents | This paper introduces the first publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, collected over 4 years and consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in ASVs by providing a multi-modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset by training and testing current deep learning-based open-source perception algorithms that have shown success in the autonomous ground vehicle domain. With the training and testing results, we discuss open challenges for existing datasets and methods, identifying future research directions. We expect that our dataset will contribute to the development of future marine autonomy pipelines and marine (field) robotics. This dataset is open source and found at https://seepersea.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18411 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles Jeong, Mingi Chadda, Arihant Ren, Ziang Zhao, Luyang Liu, Haowen Roznere, Monika Zhang, Aiwei Jiang, Yitao Achong, Sabriel Lensgraf, Samuel Li, Alberto Quattrini Robotics Computer Vision and Pattern Recognition This paper introduces the first publicly accessible labeled multi-modal perception dataset for autonomous maritime navigation, focusing on in-water obstacles within the aquatic environment to enhance situational awareness for Autonomous Surface Vehicles (ASVs). This dataset, collected over 4 years and consisting of diverse objects encountered under varying environmental conditions, aims to bridge the research gap in ASVs by providing a multi-modal, annotated, and ego-centric perception dataset, for object detection and classification. We also show the applicability of the proposed dataset by training and testing current deep learning-based open-source perception algorithms that have shown success in the autonomous ground vehicle domain. With the training and testing results, we discuss open challenges for existing datasets and methods, identifying future research directions. We expect that our dataset will contribute to the development of future marine autonomy pipelines and marine (field) robotics. This dataset is open source and found at https://seepersea.github.io/. |
| title | SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehicles |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.18411 |