A Self-Supervised Denoising Strategy for Underwater Acoustic Camera Imageries

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Xiaoteng, Mizuno, Katsunori, Zhang, Yilong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911905126285312
author Zhou, Xiaoteng
Mizuno, Katsunori
Zhang, Yilong
author_facet Zhou, Xiaoteng
Mizuno, Katsunori
Zhang, Yilong
contents In low-visibility marine environments characterized by turbidity and darkness, acoustic cameras serve as visual sensors capable of generating high-resolution 2D sonar images. However, acoustic camera images are interfered with by complex noise and are difficult to be directly ingested by downstream visual algorithms. This paper introduces a novel strategy for denoising acoustic camera images using deep learning techniques, which comprises two principal components: a self-supervised denoising framework and a fine feature-guided block. Additionally, the study explores the relationship between the level of image denoising and the improvement in feature-matching performance. Experimental results show that the proposed denoising strategy can effectively filter acoustic camera images without prior knowledge of the noise model. The denoising process is nearly end-to-end without complex parameter tuning and post-processing. It successfully removes noise while preserving fine feature details, thereby enhancing the performance of local feature matching.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02914
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Self-Supervised Denoising Strategy for Underwater Acoustic Camera Imageries
Zhou, Xiaoteng
Mizuno, Katsunori
Zhang, Yilong
Computer Vision and Pattern Recognition
Image and Video Processing
In low-visibility marine environments characterized by turbidity and darkness, acoustic cameras serve as visual sensors capable of generating high-resolution 2D sonar images. However, acoustic camera images are interfered with by complex noise and are difficult to be directly ingested by downstream visual algorithms. This paper introduces a novel strategy for denoising acoustic camera images using deep learning techniques, which comprises two principal components: a self-supervised denoising framework and a fine feature-guided block. Additionally, the study explores the relationship between the level of image denoising and the improvement in feature-matching performance. Experimental results show that the proposed denoising strategy can effectively filter acoustic camera images without prior knowledge of the noise model. The denoising process is nearly end-to-end without complex parameter tuning and post-processing. It successfully removes noise while preserving fine feature details, thereby enhancing the performance of local feature matching.
title A Self-Supervised Denoising Strategy for Underwater Acoustic Camera Imageries
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2406.02914