An End-to-End Underwater-Image-Enhancement Framework Based on Fractional Integral Retinex and Unsupervised Autoencoder

As an essential low-level computer vision task for remotely operated underwater robots and unmanned underwater vehicles to detect and understand the underwater environment, underwater image enhancement is facing challenges of light scattering, absorption, and distortion. Instead of using a specific...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Fractal and fractional Jg. 7; H. 1; S. 70
Hauptverfasser: Yu, Yang, Qin, Chenfeng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.01.2023
Schlagworte:
Algorithms
Autonomous underwater vehicles
Coders
Computer vision
Datasets
Deep learning
Distortion
Fractional calculus
fractional integral Retinex
Haze
Image enhancement
Machine vision
Robots
underwater image enhancement
Underwater robots
unsupervised autoencoder
ISSN:2504-3110, 2504-3110
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:As an essential low-level computer vision task for remotely operated underwater robots and unmanned underwater vehicles to detect and understand the underwater environment, underwater image enhancement is facing challenges of light scattering, absorption, and distortion. Instead of using a specific underwater imaging model to mitigate the degradation of underwater images, we propose an end-to-end underwater-image-enhancement framework that combines fractional integral-based Retinex and an encoder–decoder network. The proposed variant of Retinex aims to alleviate haze and color distortion in the input image while preserving edges to a large extent by utilizing a modified fractional integral filter. The encoder–decoder network with channel-wise attention modules trained in an unsupervised manner to overcome the lack of paired underwater image datasets is designed to refine the output of the Retinex. Our framework was evaluated under qualitative and quantitative metrics on several public underwater image datasets and yielded satisfactory enhancement results on the evaluation set.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2504-3110
2504-3110
DOI:10.3390/fractalfract7010070