• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

海洋环境中单目 SLAM 在水下机器人中的应用评估。

Marine Application Evaluation of Monocular SLAM for Underwater Robots.

机构信息

Acoustic Science and Technology Laboratory, Harbin Engineering University, Harbin 150001, China.

Key Laboratory of Marine Information Acquisition and Security, Harbin Engineering University, Ministry of Industry and Information Technology, Harbin 150001, China.

出版信息

Sensors (Basel). 2022 Jun 21;22(13):4657. doi: 10.3390/s22134657.

DOI:10.3390/s22134657
PMID:35808155
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9269032/
Abstract

With the development of artificial intelligence technology, visual simultaneous localization and mapping (SLAM) has become a cheap and efficient localization method for underwater robots. However, there are many problems in underwater visual SLAM, such as more serious underwater imaging distortion, more underwater noise, and unclear details. In this paper, we study these two problems and chooses the ORB-SLAM2 algorithm as the method to obtain the motion trajectory of the underwater robot. The causes of radial distortion and tangential distortion of underwater cameras are analyzed, a distortion correction model is constructed, and five distortion correction coefficients are obtained through pool experiments. Comparing the performances of contrast-limited adaptive histogram equalization (CLAHE), median filtering (MF), and dark channel prior (DCP) image enhancement methods in underwater SLAM, it is found that the DCP method has the best image effect evaluation, the largest number of oriented fast and rotated brief (ORB) feature matching, and the highest localization trajectory accuracy. The results show that the ORB-SLAM2 algorithm can effectively locate the underwater robot, and the correct distortion correction coefficient and DCP improve the stability and accuracy of the ORB-SLAM2 algorithm.

摘要

随着人工智能技术的发展，视觉同时定位与建图（SLAM）已成为水下机器人的一种廉价高效的定位方法。然而，水下视觉 SLAM 存在许多问题，例如更严重的水下成像失真、更多的水下噪声以及不清晰的细节。本文针对这两个问题展开研究，选择 ORB-SLAM2 算法作为获取水下机器人运动轨迹的方法。分析了水下相机径向和切向失真的原因，建立了失真校正模型，并通过水池实验得到了五个失真校正系数。比较了对比度受限自适应直方图均衡化（CLAHE）、中值滤波（MF）和暗通道先验（DCP）三种水下 SLAM 图像增强方法的性能，发现 DCP 方法具有最佳的图像效果评价、最大的定向快速旋转布（ORB）特征匹配数量和最高的定位轨迹精度。结果表明，ORB-SLAM2 算法能有效地对水下机器人进行定位，正确的失真校正系数和 DCP 提高了 ORB-SLAM2 算法的稳定性和准确性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/e5168153c940/sensors-22-04657-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/7dc199158673/sensors-22-04657-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/3348417d7780/sensors-22-04657-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/d1d01639ad7b/sensors-22-04657-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/95c7eccbcf6a/sensors-22-04657-g004a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/94824bfa546a/sensors-22-04657-g005a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/2bbd344246af/sensors-22-04657-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/93e3d86dc864/sensors-22-04657-g007a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/8af7c5ce2804/sensors-22-04657-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/49e3d056d180/sensors-22-04657-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/e5ec8b19c556/sensors-22-04657-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/d9f2dbd179d9/sensors-22-04657-g011a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/b7daba5a64ae/sensors-22-04657-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/171c8bbbaa61/sensors-22-04657-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/e5168153c940/sensors-22-04657-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/7dc199158673/sensors-22-04657-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/3348417d7780/sensors-22-04657-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/d1d01639ad7b/sensors-22-04657-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/95c7eccbcf6a/sensors-22-04657-g004a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/94824bfa546a/sensors-22-04657-g005a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/2bbd344246af/sensors-22-04657-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/93e3d86dc864/sensors-22-04657-g007a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/8af7c5ce2804/sensors-22-04657-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/49e3d056d180/sensors-22-04657-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/e5ec8b19c556/sensors-22-04657-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/d9f2dbd179d9/sensors-22-04657-g011a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/b7daba5a64ae/sensors-22-04657-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/171c8bbbaa61/sensors-22-04657-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/6885/9269032/e5168153c940/sensors-22-04657-g014.jpg

相似文献

1
Marine Application Evaluation of Monocular SLAM for Underwater Robots.海洋环境中单目 SLAM 在水下机器人中的应用评估。
Sensors (Basel). 2022 Jun 21;22(13):4657. doi: 10.3390/s22134657.
2
Study on the Influence of Image Noise on Monocular Feature-Based Visual SLAM Based on FFDNet.基于FFDNet的图像噪声对基于单目特征的视觉同步定位与地图构建的影响研究
Sensors (Basel). 2020 Aug 31;20(17):4922. doi: 10.3390/s20174922.
3
A robust approach for a filter-based monocular simultaneous localization and mapping (SLAM) system.一种基于滤波器的单目同时定位与建图（SLAM）系统的鲁棒方法。
Sensors (Basel). 2013 Jul 3;13(7):8501-22. doi: 10.3390/s130708501.
4
Semantic visual simultaneous localization and mapping (SLAM) using deep learning for dynamic scenes.使用深度学习的语义视觉同步定位与地图构建（SLAM）用于动态场景。
PeerJ Comput Sci. 2023 Oct 10;9:e1628. doi: 10.7717/peerj-cs.1628. eCollection 2023.
5
SLAMM: Visual monocular SLAM with continuous mapping using multiple maps.SLAMM：使用多地图进行连续映射的视觉单目 SLAM。
PLoS One. 2018 Apr 27;13(4):e0195878. doi: 10.1371/journal.pone.0195878. eCollection 2018.
6
An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot.基于改进深度残差网络的单目视觉机器人语义同时定位与建图方法。
Comput Intell Neurosci. 2020 Feb 10;2020:7490840. doi: 10.1155/2020/7490840. eCollection 2020.
7
RU-SLAM: A Robust Deep-Learning Visual Simultaneous Localization and Mapping (SLAM) System for Weakly Textured Underwater Environments.RU-SLAM：一种用于弱纹理水下环境的鲁棒深度学习视觉同步定位与地图构建（SLAM）系统。
Sensors (Basel). 2024 Mar 18;24(6):1937. doi: 10.3390/s24061937.
8
RGBD-Inertial Trajectory Estimation and Mapping for Ground Robots.地面机器人的RGBD惯性轨迹估计与建图
Sensors (Basel). 2019 May 15;19(10):2251. doi: 10.3390/s19102251.
9
AEKF-SLAM: A New Algorithm for Robotic Underwater Navigation.AEKF-SLAM：一种用于机器人水下导航的新算法。
Sensors (Basel). 2017 May 21;17(5):1174. doi: 10.3390/s17051174.
10
Underwater low-light enhancement network based on bright channel prior and attention mechanism.基于亮通道先验和注意力机制的水下低光增强网络。
PLoS One. 2023 Feb 2;18(2):e0281093. doi: 10.1371/journal.pone.0281093. eCollection 2023.

引用本文的文献

1
Advancements in Sensor Fusion for Underwater SLAM: A Review on Enhanced Navigation and Environmental Perception.水下同时定位与地图构建中传感器融合的进展：增强导航与环境感知综述
Sensors (Basel). 2024 Nov 24;24(23):7490. doi: 10.3390/s24237490.
2
Enhancing Underwater SLAM Navigation and Perception: A Comprehensive Review of Deep Learning Integration.增强水下同时定位与地图构建导航及感知：深度学习集成的全面综述
Sensors (Basel). 2024 Oct 31;24(21):7034. doi: 10.3390/s24217034.

本文引用的文献

1
Underwater image enhancement by wavelength compensation and dehazing.水下图像的波长补偿与去雾增强。
IEEE Trans Image Process. 2012 Apr;21(4):1756-69. doi: 10.1109/TIP.2011.2179666. Epub 2011 Dec 13.
2
Single Image Haze Removal Using Dark Channel Prior.基于暗通道先验的单幅图像去雾。
IEEE Trans Pattern Anal Mach Intell. 2011 Dec;33(12):2341-53. doi: 10.1109/TPAMI.2010.168. Epub 2010 Sep 9.
3
MonoSLAM: real-time single camera SLAM.单目即时定位与地图构建（MonoSLAM）：实时单目相机即时定位与地图构建
IEEE Trans Pattern Anal Mach Intell. 2007 Jun;29(6):1052-67. doi: 10.1109/TPAMI.2007.1049.
4
Improving motion estimation by accounting for local image distortion.通过考虑局部图像失真来改进运动估计。
Ultrasonics. 2004 Oct;43(1):57-65. doi: 10.1016/j.ultras.2004.02.022.