Reliable and Effective Stereo Matching for Underwater Scenes

Stereo matching plays a vital role in underwater environments, where accurate depth estimation is crucial for applications such as robotics and marine exploration. However, underwater imaging presents significant challenges, including noise, blurriness, and optical distortions that hinder effective...

Full description

Saved in:
Bibliographic Details
Main Authors: Lvwei Zhu, Ying Gao, Jiankai Zhang, Yongqing Li, Xueying Li
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/23/4570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849220438420357120
author Lvwei Zhu
Ying Gao
Jiankai Zhang
Yongqing Li
Xueying Li
author_facet Lvwei Zhu
Ying Gao
Jiankai Zhang
Yongqing Li
Xueying Li
author_sort Lvwei Zhu
collection DOAJ
description Stereo matching plays a vital role in underwater environments, where accurate depth estimation is crucial for applications such as robotics and marine exploration. However, underwater imaging presents significant challenges, including noise, blurriness, and optical distortions that hinder effective stereo matching. This study develops two specialized stereo matching networks: UWNet and its lightweight counterpart, Fast-UWNet. UWNet utilizes self- and cross-attention mechanisms alongside an adaptive 1D-2D cross-search to enhance cost volume representation and refine disparity estimation through a cascaded update module, effectively addressing underwater imaging challenges. Due to the need for timely responses in underwater operations by robots and other devices, real-time processing speed is critical for task completion. Fast-UWNet addresses this challenge by prioritizing efficiency, eliminating the reliance on the time-consuming recurrent updates commonly used in traditional methods. Instead, it directly converts the cost volume into a set of disparity candidates and their associated confidence scores. Adaptive interpolation, guided by content and confidence information, refines the cost volume to produce the final accurate disparity. This streamlined approach achieves an impressive inference speed of 0.02 s per image. Comprehensive tests conducted in diverse underwater settings demonstrate the effectiveness of both networks, showcasing their ability to achieve reliable depth perception.
format Article
id doaj-art-11e6abed16ea4a688328af0883165681
institution Kabale University
issn 2072-4292
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-11e6abed16ea4a688328af08831656812024-12-13T16:31:18ZengMDPI AGRemote Sensing2072-42922024-12-011623457010.3390/rs16234570Reliable and Effective Stereo Matching for Underwater ScenesLvwei Zhu0Ying Gao1Jiankai Zhang2Yongqing Li3Xueying Li4School of Data Science, Qingdao University of Science and Technology, Qingdao 266061, ChinaSchool of Data Science, Qingdao University of Science and Technology, Qingdao 266061, ChinaSchool of Data Science, Qingdao University of Science and Technology, Qingdao 266061, ChinaSchool of Data Science, Qingdao University of Science and Technology, Qingdao 266061, ChinaSchool of Data Science, Qingdao University of Science and Technology, Qingdao 266061, ChinaStereo matching plays a vital role in underwater environments, where accurate depth estimation is crucial for applications such as robotics and marine exploration. However, underwater imaging presents significant challenges, including noise, blurriness, and optical distortions that hinder effective stereo matching. This study develops two specialized stereo matching networks: UWNet and its lightweight counterpart, Fast-UWNet. UWNet utilizes self- and cross-attention mechanisms alongside an adaptive 1D-2D cross-search to enhance cost volume representation and refine disparity estimation through a cascaded update module, effectively addressing underwater imaging challenges. Due to the need for timely responses in underwater operations by robots and other devices, real-time processing speed is critical for task completion. Fast-UWNet addresses this challenge by prioritizing efficiency, eliminating the reliance on the time-consuming recurrent updates commonly used in traditional methods. Instead, it directly converts the cost volume into a set of disparity candidates and their associated confidence scores. Adaptive interpolation, guided by content and confidence information, refines the cost volume to produce the final accurate disparity. This streamlined approach achieves an impressive inference speed of 0.02 s per image. Comprehensive tests conducted in diverse underwater settings demonstrate the effectiveness of both networks, showcasing their ability to achieve reliable depth perception.https://www.mdpi.com/2072-4292/16/23/4570underwater imagingstereo matchingdepth estimation
spellingShingle Lvwei Zhu
Ying Gao
Jiankai Zhang
Yongqing Li
Xueying Li
Reliable and Effective Stereo Matching for Underwater Scenes
Remote Sensing
underwater imaging
stereo matching
depth estimation
title Reliable and Effective Stereo Matching for Underwater Scenes
title_full Reliable and Effective Stereo Matching for Underwater Scenes
title_fullStr Reliable and Effective Stereo Matching for Underwater Scenes
title_full_unstemmed Reliable and Effective Stereo Matching for Underwater Scenes
title_short Reliable and Effective Stereo Matching for Underwater Scenes
title_sort reliable and effective stereo matching for underwater scenes
topic underwater imaging
stereo matching
depth estimation
url https://www.mdpi.com/2072-4292/16/23/4570
work_keys_str_mv AT lvweizhu reliableandeffectivestereomatchingforunderwaterscenes
AT yinggao reliableandeffectivestereomatchingforunderwaterscenes
AT jiankaizhang reliableandeffectivestereomatchingforunderwaterscenes
AT yongqingli reliableandeffectivestereomatchingforunderwaterscenes
AT xueyingli reliableandeffectivestereomatchingforunderwaterscenes