Wave height measurement scheme using wave detector based on convolutional neural network and PPM calculator with ocean wave images

IF 2.3 3区工程技术 Q2 ENGINEERING, MARINE

International Journal of Naval Architecture and Ocean Engineering Pub Date : 2023-01-01 DOI:10.1016/j.ijnaoe.2023.100542

Il-Kyu Hwang , Minkyu Lee , Junsub Han , Jeeun Choi

{"title":"Wave height measurement scheme using wave detector based on convolutional neural network and PPM calculator with ocean wave images","authors":"Il-Kyu Hwang , Minkyu Lee , Junsub Han , Jeeun Choi","doi":"10.1016/j.ijnaoe.2023.100542","DOIUrl":null,"url":null,"abstract":"<div><p>The measurement of wave height is essential for weather analysis, safe navigation of ships, and ship design. This study proposes a low-cost and direct method for measuring wave height using ocean wave images. The proposed scheme comprises a Wave Detector based on Convolutional Neural Networks that takes two-dimensional ocean images as input, and a PPM Calculator that measures the size of an object in the image. The study explains the configuration and implementation of the Wave Detector and the basic principle of the PPM surface generating method for the PPM Calculator, with support from ground experiments. The proposed scheme is validated using two types of wave height measurement sensors and three types of real ocean images for the Wave Detector, as well as two rounds of ground experiments for the PPM Calculator.</p><p>The results show that the wave height values measured by the proposed scheme are highly consistent with the values from the measurement sensors.</p></div>","PeriodicalId":14160,"journal":{"name":"International Journal of Naval Architecture and Ocean Engineering","volume":"15 ","pages":"Article 100542"},"PeriodicalIF":2.3000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Naval Architecture and Ocean Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2092678223000316","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MARINE","Score":null,"Total":0}

引用次数: 0

Abstract

The measurement of wave height is essential for weather analysis, safe navigation of ships, and ship design. This study proposes a low-cost and direct method for measuring wave height using ocean wave images. The proposed scheme comprises a Wave Detector based on Convolutional Neural Networks that takes two-dimensional ocean images as input, and a PPM Calculator that measures the size of an object in the image. The study explains the configuration and implementation of the Wave Detector and the basic principle of the PPM surface generating method for the PPM Calculator, with support from ground experiments. The proposed scheme is validated using two types of wave height measurement sensors and three types of real ocean images for the Wave Detector, as well as two rounds of ground experiments for the PPM Calculator.

The results show that the wave height values measured by the proposed scheme are highly consistent with the values from the measurement sensors.

查看原文本刊更多论文

基于卷积神经网络的检波器和PPM计算器的海浪图像波高测量方案

波浪高度的测量对于天气分析、船舶安全航行和船舶设计是必不可少的。本研究提出了一种低成本、直接的利用海浪图像测量浪高的方法。该方案包括一个基于卷积神经网络的波浪探测器，以二维海洋图像为输入，以及一个PPM计算器，测量图像中物体的大小。本文以地面实验为依托，阐述了测波仪的结构与实现，以及PPM计算器的PPM曲面生成方法的基本原理。利用两种波高测量传感器和三种真实海洋图像对该方案进行了验证，并对PPM计算器进行了两轮地面实验。结果表明，该方案测得的波高值与测量传感器测得的波高值高度一致。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Naval Architecture and Ocean Engineering ENGINEERING, MARINE-

CiteScore

4.90

自引率

4.50%

发文量

审稿时长

12 months

期刊介绍： International Journal of Naval Architecture and Ocean Engineering provides a forum for engineers and scientists from a wide range of disciplines to present and discuss various phenomena in the utilization and preservation of ocean environment. Without being limited by the traditional categorization, it is encouraged to present advanced technology development and scientific research, as long as they are aimed for more and better human engagement with ocean environment. Topics include, but not limited to: marine hydrodynamics; structural mechanics; marine propulsion system; design methodology & practice; production technology; system dynamics & control; marine equipment technology; materials science; underwater acoustics; ocean remote sensing; and information technology related to ship and marine systems; ocean energy systems; marine environmental engineering; maritime safety engineering; polar & arctic engineering; coastal & port engineering; subsea engineering; and specialized watercraft engineering.