多种波浪图像特征点提取匹配算法结果对比研究  

COMPARISON AND RESEARCH OF MULTIPLE ALGORITHMS FOR EXTRACTING AND MATCHING WAVE IMAGE FEATURE POINTS

作　　者：刘晔恒 王千 李晔 LIU Yeheng;WANG Qian;LI Ye(School of Ocean and Civil Engineering,Shanghai Jiao Tong University,Shanghai 200040,China;Department of Ocean Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,Guangdong,China)

机构地区：[1]上海交通大学船舶海洋与建筑工程学院,上海200040 [2]南方科技大学海洋科学与工程系,广东深圳518055

出　　处：《力学与实践》2024年第6期1154-1165,共12页Mechanics in Engineering

基　　金：国家自然科学基金资助项目(12102262)。

摘　　要：为了通过非接触的手段获取实验室波浪数据,本文探讨了多种波浪高度场监测技术,对比了基于双目视觉的不同图像特征提取与匹配算法的应用效果,在多功能拖曳水池内开展了实验,并根据双目相机捕获的波面动态图像数据,对图像进行了特征点的定位与匹配,实现了波浪三维形态的高精度重建。通过对不同特征提取与匹配算法实际应用效果的评估,给出了提升波浪监测技术精准度与适用性方法的实验依据与技术支撑。In order to obtain laboratory wave data through non-contact means,this article explores various wave height field monitoring technologies,compares the application effects of different image feature extraction and matching algorithms based on binocular vision,conducts experiments in a multi-functional towing tank,and locates and matches image feature points based on the dynamic image data captured by binocular cameras,achieving high-precision reconstruction of the three-dimensional shape of waves.Through the evaluation of the practical application effects of different feature extraction and matching algorithms,the experimental basis and technical support for improving the accuracy and applicability of wave monitoring technology are provided.

关 键 词：双目重构 图像算法 波面形态 物理实验 

分 类 号：P714.1[天文地球—海洋科学] TP391.4[自动化与计算机技术—计算机应用技术]