The Marine Debris Forward-Looking Sonar Datasets

Matias Valdenegro Toro; Deepan Chakravarthi Padmanabhan; Deepak Singh; Bilal Wehbe; Yvan Petillot

doi:10.1109/oceans58557.2025.11104623

The Marine Debris Forward-Looking Sonar Datasets

Matias Valdenegro Toro
, Deepan Chakravarthi Padmanabhan
, Deepak Singh
, Bilal Wehbe
, Yvan Petillot

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Sonar sensing is fundamental for underwater robotics, but limited by capabilities of AI systems, which need large training datasets. Public data in sonar modalities is lacking. This paper presents the Marine Debris Forward-Looking Sonar datasets, with three different settings (watertank, turntable, flooded quarry) increasing dataset diversity and multiple computer vision tasks: object classification, object detection, semantic segmentation, patch matching, and unsupervised learning. We provide full dataset description, basic analysis and initial results for some tasks. We expect the research community will benefit from this dataset, which is publicly available at https://doi.org/10.5281/zenodo.15101686.

Original language	English
Title of host publication	OCEANS 2025 Brest
Publisher	IEEE
ISBN (Electronic)	9798331537470
ISBN (Print)	9798331537487
DOIs	https://doi.org/10.1109/oceans58557.2025.11104623
Publication status	Published - 11 Aug 2025
Event	OCEANS 2025 Brest Conference - Le Quartz, Brest, France Duration: 16 Jun 2025 → 19 Jun 2025 https://brest25.oceansconference.org/

Conference

Conference	OCEANS 2025 Brest Conference
Country/Territory	France
City	Brest
Period	16/06/25 → 19/06/25
Internet address	https://brest25.oceansconference.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

Training
Computer vision
semantic segmentation
oceans
sonar
object detection
robot sensing systems
sensors
unsupervised learning
sonar detection

ASJC Scopus subject areas

Oceanography
Ocean Engineering

Access to Document

10.1109/oceans58557.2025.11104623

Cite this

@inproceedings{4ff2af55b780405481375d8028bb6290,

title = "The Marine Debris Forward-Looking Sonar Datasets",

abstract = "Sonar sensing is fundamental for underwater robotics, but limited by capabilities of AI systems, which need large training datasets. Public data in sonar modalities is lacking. This paper presents the Marine Debris Forward-Looking Sonar datasets, with three different settings (watertank, turntable, flooded quarry) increasing dataset diversity and multiple computer vision tasks: object classification, object detection, semantic segmentation, patch matching, and unsupervised learning. We provide full dataset description, basic analysis and initial results for some tasks. We expect the research community will benefit from this dataset, which is publicly available at https://doi.org/10.5281/zenodo.15101686.",

keywords = "Training, Computer vision, semantic segmentation, oceans, sonar, object detection, robot sensing systems, sensors, unsupervised learning, sonar detection",

author = "\{Valdenegro Toro\}, Matias and Padmanabhan, \{Deepan Chakravarthi\} and Deepak Singh and Bilal Wehbe and Yvan Petillot",

year = "2025",

month = aug,

day = "11",

doi = "10.1109/oceans58557.2025.11104623",

language = "English",

isbn = "9798331537487",

booktitle = "OCEANS 2025 Brest",

publisher = "IEEE",

address = "United States",

note = "OCEANS 2025 Brest Conference ; Conference date: 16-06-2025 Through 19-06-2025",

url = "https://brest25.oceansconference.org/",

}

TY - GEN

T1 - The Marine Debris Forward-Looking Sonar Datasets

AU - Valdenegro Toro, Matias

AU - Padmanabhan, Deepan Chakravarthi

AU - Singh, Deepak

AU - Wehbe, Bilal

AU - Petillot, Yvan

PY - 2025/8/11

Y1 - 2025/8/11

N2 - Sonar sensing is fundamental for underwater robotics, but limited by capabilities of AI systems, which need large training datasets. Public data in sonar modalities is lacking. This paper presents the Marine Debris Forward-Looking Sonar datasets, with three different settings (watertank, turntable, flooded quarry) increasing dataset diversity and multiple computer vision tasks: object classification, object detection, semantic segmentation, patch matching, and unsupervised learning. We provide full dataset description, basic analysis and initial results for some tasks. We expect the research community will benefit from this dataset, which is publicly available at https://doi.org/10.5281/zenodo.15101686.

AB - Sonar sensing is fundamental for underwater robotics, but limited by capabilities of AI systems, which need large training datasets. Public data in sonar modalities is lacking. This paper presents the Marine Debris Forward-Looking Sonar datasets, with three different settings (watertank, turntable, flooded quarry) increasing dataset diversity and multiple computer vision tasks: object classification, object detection, semantic segmentation, patch matching, and unsupervised learning. We provide full dataset description, basic analysis and initial results for some tasks. We expect the research community will benefit from this dataset, which is publicly available at https://doi.org/10.5281/zenodo.15101686.

KW - Training

KW - Computer vision

KW - semantic segmentation

KW - oceans

KW - sonar

KW - object detection

KW - robot sensing systems

KW - sensors

KW - unsupervised learning

KW - sonar detection

UR - https://www.scopus.com/pages/publications/105015034700

U2 - 10.1109/oceans58557.2025.11104623

DO - 10.1109/oceans58557.2025.11104623

M3 - Conference contribution

SN - 9798331537487

BT - OCEANS 2025 Brest

PB - IEEE

T2 - OCEANS 2025 Brest Conference

Y2 - 16 June 2025 through 19 June 2025

ER -

The Marine Debris Forward-Looking Sonar Datasets

Abstract

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this