[1]张会珍,徐相龙,王立杰,等.基于深度学习的海浪参数观测方法[J].机械与电子,2025,(10):3-10.
　ZHANG Huizhen,XU Xianglong,WANG Lijie,et al.A Deep Learning-based Framework for Ocean Wave Parameter Estimation[J].Machinery & Electronics,2025,(10):3-10.
点击复制

基于深度学习的海浪参数观测方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2025年10期
页码:
3-10
栏目:
研究与设计
出版日期:
2025-10-25

文章信息/Info

Title:
A Deep Learning-based Framework for Ocean Wave Parameter Estimation
文章编号:
1001-2257 ( 2025 ) 10-0003-08
作者:
张会珍; 徐相龙; 王立杰; 高嘉伟; 侯 男
东北石油大学电气信息工程学院,黑龙江 大庆 163000
Author(s):
ZHANG Huizhen ;  XU Xianglong ;  WANG Lijie ;  GAO Jiawei ;  HOU Nan
( School of Electrical and Information Engineering , Northeast Petroleum University , Daqing 163000 , China )
关键词:
深度学习; 视差估计; 海浪观测; 三维点云
Keywords:
deep learning ;  disparity estimation ;  ocean wave observation ;  3D point cloud
分类号:
TP391.4
文献标志码:
A
摘要:
针对传统观测方法在复杂背景下效果较差、计算效率低的问题,提出一种改进的深度学习海浪观测算法。通过直接计算海浪图像对中的视差图,显著提升观测效率。所设计网络包含特征提取、3D 卷积和视差回归模块。特征提取阶段引入空洞空间金字塔池化( ASPP )模块,提取多尺度空间特征,并结合注意力机制优化特征融合,构建多分支匹配代价体。 3D 卷积网络采用堆叠式编码 解码结构,对代价体进行规则化,提取特征点对应关系。基于 Acqua Alta 数据集的评估结果表明,相较于传统算法,所提方法在保证重建精度的同时,计算效率提升近 75% ,充分满足海浪观测的高效性与准确性要求,具有重要的理论意义与工程应用前景。
Abstract:
To address the limitations of traditional wave observation methods in complex backgrounds , such as poor robustness and low computational efficiency , this study proposes an improved deep learning based wave observation algorithm.The method directly estimates disparity maps from stereo wave images , significantly enhancing processing efficiency.The proposed network architecture consists of three main modules : feature extraction , 3D convolution , and disparity regression.In the feature extraction stage , an Atrous Spatial Pyramid Pooling ( ASPP ) module is introduced to capture multi-scale spatial features.An attention mechanism is further integrated to optimize feature fusion , enabling the construction of a multi branch cost volume.A stacked encoder decoder structure based on 3D convolution is employed to regularize the cost volume and extract reliable point correspondences.Experimental results on the Acqua Alta dataset demonstrate that , compared with traditional approaches , the proposed method achieves comparable reconstruction accuracy while improving computational efficiency by approximately 75%.These results highlight the method ’ s potential for high-efficiency and high-precision wave observation , with significant theoretical and engineering implications.

参考文献/References:

[ 1 ] 周庆伟,张松,武贺,等 . 海洋波浪观测技术综述[ J ] . 海洋测绘,2016 , 36 ( 2 ): 39-44.

[ 2 ] 张文祥 . 当前国际海洋观测技术的主要发展方向[ J ] .上海国土资源,2015 , 36 ( 2 ): 98-100.
[ 3 ] BENETAZZO A.Measurements of short water waves using stereo matched image sequences [ J ] .Coastal engineering , 2006 , 53 ( 12 ): 1013-1032.
[ 4 ] WANEK J M , WU C H.Automated trinocular stereo imaging system for three-dimensional surface wave measurements [ J ] .Ocean engineering , 2006 , 33 ( 5 / 6 ):723-747.
[ 5 ] WANG X L , WEI G , DU H , et al.Reconstruction of 3-D surface waves generated by moving submerged sphere based on stereo imaging principle [ J ] .Journal of hydrodynamics , 2020 , 32 ( 1 ): 139-147.
[ 6 ] ALBERELLO A , BENNETTS L G , ONORATO M , et al.Three-dimensional imaging of waves and floes in the marginal ice zone during a cyclone [ J ] Nature communications , 2022 , 13 ( 1 ): 4590.
[ 7 ] MAYER N , ILG E , HAUSSER P , et al.A large dataset to train convolutional networks for disparity , optical flow , and scene flow estimation [ C ]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2016 : 4040-4048.
[ 8 ] KENDALL A , MARTIROSYAN H , DASGUPTA S , et al.End-to-end learning of geometry and context for deep stereo regression [ C ]// Proceedings of the IEEE International Conference on Computer Vision , 2017 : 66-75.
[ 9 ] CHANG J R , CHEN Y S.Pyramid stereo matching network [ C ] ∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 5410-5418.
[ 10 ] PISTELLATO M , BERGAMASCO F , TORSELLO A , et al.A physics-driven CNN model for real time sea waves 3D reconstruction [ J ] .Remote sensing , 2021 , 13 ( 18 ): 3780.
[ 11 ] HUANG J J , XU F , CHEN T B , et al.Real-time o- cean waves three-dimensional reconstruction research based on deep learning [ C ]// 2023 2nd International Conference on Robotics , Artificial Intelligence and Intelligent Control ( RAIIC ), New York : IEEE , 2023 : 334-339.
[ 12 ] YANG Y , LU C W , LI Z H.Deep-learning-based stereo matching of long-distance sea surface images for sea level monitoring systems [ J ] .Journal of marine science and engineering , 2024 , 12 ( 6 ): 961.
[ 13 ] WU J J , CHEN S Z , LIU S X , et al.Research on wave measurement and simulation experiments of binocular stereo vision based on intelligent feature matching [ J ] .Frontiers in marine science , 2024 , 11 : 1508233.
[ 14 ] 张学超,李向峰,史玉锋,等 . 海洋能发展现状及展望[ J ] . 科技视界, 2015 ( 16 ): 258.
[ 15 ] WOO S , PARK J , LEE J Y , et al.Cbam : convolutional block attention module [ C ]// Proceedings of the European Conference on Computer Vision ( ECCV ),2018 : 3-19.
[ 16 ] 尹传历,刘冬梅,宋建中 . 改进的基于图像分割的立体匹配算法[ J ] . 计算机辅助设计与图形学学报, 2008 , 20 ( 6 ): 808-812.
[ 17 ] 朱丽娜,刘飞 . 基于 Wallis 滤波的改进小波去噪方法研究[ J ] . 地理空间信息, 2006 , 4 ( 6 ): 55-56.
[ 18 ] FISCHLER M A , BOLLES R C.Random sample consensus : a paradigm for model fitting with applications to image analysis and automated cartography [ J ] .Communication of the ACM , 1981 , 24 ( 6 ): 381-395.

相似文献/References:

[1]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
　WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(10):29.
[2]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
　LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(10):67.
[3]肖倩宏,康 鹏,杜 江,等.深度学习在电网智能调控系统中应用研究[J].机械与电子,2021,(01):38.
　XIAO Qianhong,KANG Peng,DU Jiang,et al.Research on the Application of Deep Learning Theory in Power Grid Intelligent Dispatching[J].Machinery & Electronics,2021,(10):38.
[4]许 哲,张少帅,郭 璐,等.无人机深度学习去雾算法[J].机械与电子,2021,(04):13.
　XU Zhe,ZHANG Shaoshuai,GUO Lu,et al. Deep Learning Defogging Algorithm for UAV[J].Machinery & Electronics,2021,(10):13.
[5]齐爱玲１,李 琳１,朱亦轩２,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
　QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(10):15.
[6]徐先峰,郑少杰,赵 依,等.基于数据分解与重构的光伏发电功率超短期预测[J].机械与电子,2022,(04):20.
　XU Xianfeng,ZHENG Shaojie,ZHAO Yi,et al.Ultra-short-term Prediction of Photovoltaic Power Generation Based on Data Decomposition and Deconstruction[J].Machinery & Electronics,2022,(10):20.
[7]江 励,熊达明,汤健华,等.自然光线环境中的空间物体快速识别和定位算法研究[J].机械与电子,2022,(06):8.
　JIANG Li,XIONG Daming,TANG Jianhua,et al.Recognition and Positioning Algorithm of Space Objects in Natural Light Environment[J].Machinery & Electronics,2022,(10):8.
[8]王西志,管声启,张理博,等.基于视觉引导的工业棒材上料系统研究[J].机械与电子,2023,41(05):19.
　WANG Xizhi,GUAN Shengqi,ZHANG Libo,et al.Research on Industrial Bar Feeding System Based on Visual Guidance[J].Machinery & Electronics,2023,41(10):19.
[9]王 青,吕绪山,党 帅,等.基于深度学习的纱管识别方法研究[J].机械与电子,2023,41(12):20.
　WANG Qing,LYU Xushan,DANG Shuai,et al.Research on Yarn Bobbin Detection Method Based on Deep Learning[J].Machinery & Electronics,2023,41(10):20.
[10]姜越夫,王 青,吕绪山.改进 YOLOv5s 的纱管目标检测方法[J].机械与电子,2024,42(02):29.
　JIANG Yuefu,WANG Qing,LYU Xushan.Improved YOLOv5s Method for Yarn Tube Object Detection[J].Machinery & Electronics,2024,42(10):29.

备注/Memo

备注/Memo:
收稿日期: 2025-04-27
基金项目:国家自然科学基金资助项目( 2021JJLH0025 )
作者简介:张会珍 ( 1979- ),女,天津人,博士,副教授,研究方向为检测技术与自动化装置;徐相龙 ( 2000- ),男,黑龙江哈尔滨人,硕士研究生,研究方向为模式识别与应用,通信作者, E-mail : 2750685958@qq.com 。
更新日期/Last Update: 2025-11-12