COU: Common Objects Underwater

Loading...
Thumbnail Image

Persistent link to this item

Statistics
View Statistics

Keywords

Collection period

2022-09-01
2024-02-07

Date completed

2025-02-11

Date updated

Time period coverage

Geographic coverage

Source information

Journal Title

Journal ISSN

Volume Title

Title

COU: Common Objects Underwater

Published Date

2025-02-27

Author Contact

Sattar, Junaed
junaed@umn.edu

Type

Dataset
Field Study Data
Experimental Data

Abstract

We introduce COU: Common Objects Underwater, an instance-segmented image dataset of commonly found man-made objects in multiple aquatic and marine environments. COU contains approximately 10K segmented images, annotated from images collected during a number of underwater robot field trials in diverse locations. COU has been created to address the lack of datasets with robust class coverage curated for underwater instance segmentation, which is particularly useful for training light-weight, real-time capable detectors for Autonomous Underwater Vehicles (AUVs). In addition, COU addresses the lack of diversity in object classes since the commonly available aquatic image datasets focus only on marine life. Currently, COU contains images from both closed-water (pool) and open-water (lakes and oceans) environments, of 24 different classes of objects including marine debris, dive tools, and AUVs To assess the efficacy of COU in training underwater object detectors, we use three state-of-the-art models to evaluate its performance and accuracy, using a combination of standard accuracy and efficiency metrics. The improved performance of COU-trained detectors over those solely trained on terrestrial data demonstrates the clear advantage of the availability of annotated underwater images.

Description

1. YOLO File List (all of these files are present in YOLO.zip) A. Filename: images.zip Short description: This compressed folder contains the images of the COU dataset in jpg format split into train, test, and val directories. images - | train - | test - | val - B. Filename: labels.zip Short description: This compressed folder contains the annotation labels of the COU dataset in the YOLO label format split into train, test, and val directories. labels - | train - | test - | val - C. Filename: obj.names Short description: This file contains the class names required for YOLO models. D. Filename: dataset.yaml Short description: This file contains the relevant dataset information for training a YOLO model. 2. Additional Filename: coco.zip Short description: This file contains the dataset in the COCO format. | coco - | train_annotations.json | test_annotations.json | val_annotations.json | images -

Referenced by

Related to

Replaces

item.page.isreplacedby

Publisher

Funding information

item.page.sponsorshipfunderid

item.page.sponsorshipfundingagency

item.page.sponsorshipgrant

Previously Published Citation

Other identifiers

Suggested citation

Sattar, Junaed; Mukherjee, Rishi; Singh, Sakshi; McWilliams, Jack. (2025). COU: Common Objects Underwater. Retrieved from the Data Repository for the University of Minnesota (DRUM), https://hdl.handle.net/11299/270146.

Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.