Underwater Visual Signals Recognition Dataset (UVSRD)

Citation Author(s):
Hamilton
Saquín
Submitted by:
Cristian Sanchez
Last updated:
Wed, 01/22/2025 - 11:00
DOI:
10.21227/ew07-nd78
Data Format:
*.avi; *.png; *.csv; *.zip
License:
Creative Commons Attribution
266 Views
Categories:
Artificial Intelligence
Machine Learning
Image Processing
Computational Intelligence
Computer Vision
Keywords:
computer vision, underwater vision, Underwater image, image classification, Deep Learning, convolutional neural network, image restorage, image enhance.
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

This dataset comprises 33,800 images of underwater signals captured in aquatic environments. Each signal is presented against three types of backgrounds: pool, marine, and plain white. Additionally, the dataset includes three water tones: clear, blue, and green. A total of 12 different signals are included, each available in all six possible background-tone combinations.

This dataset is ideal for image enhancement and restoration using computer vision or deep learning techniques. It can also be applied to the classification and segmentation of underwater signals in diverse aquatic settings.

Instructions: 

This dataset can be used for any application in image restoration and enhancement, computer vision, and image segmentation in marine environments. If this dataset is used, the article titled AquaSignalNet: An Autonomous Underwater Signal Recognition System for ROV Control Using CNN and this dataset must be cited.

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?