融合多尺度旋转锚机制的海洋中尺度涡自动检测  

Multi-scale rotating anchor mechanism based automatic detection of ocean mesoscale eddy

作　　者：杜艳玲[1] 刘倩倩 王丽丽 徐鑫 魏泉苗 宋巍 Du Yanling;Liu Qianqian;Wang Lili;Xu Xin;Wei Quanmiao;Song Wei(College of Information,Shanghai Ocean University,Shanghai 201306,China;East China Sea Bureau of Ministry of Natural Resources,Shanghai 200136,China)

机构地区：[1]上海海洋大学信息学院,上海201306 [2]自然资源部东海局,上海200136

出　　处：《中国图象图形学报》2022年第10期3092-3101,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(41906179);上海市自然科学基金项目(18ZR1417300)。

摘　　要：目的海洋中尺度涡自动检测是了解其演变规律,研究其在海洋物质运输和能量传递中的作用的基础。针对海洋中尺度涡形态不规则、结构复杂多变、长宽比不确定,以及涡群海域中尺度涡分布密集导致的检测精度低的问题,提出一种基于深度学习多尺度旋转锚机制的海洋中尺度涡自动旋转检测方法。方法首先对卫星遥感海平面高度异常数据进行可视化预处理,并采用图像处理策略对数据集进行扩充构建训练集;其次构建了一种基于深度学习多尺度旋转锚机制的中尺度涡自动检测模型,考虑到中尺度涡尺度变化大和其所处海洋环境复杂多变的特点,主干网络采用RetinaNet提取中尺度涡特征,同时采用特征金字塔结构融合中尺度涡的低层与高层特征,设计多尺度、多长宽比以及多旋转角度锚点机制实现多尺度旋转检测锚的生成;最后集成分类与回归两个子网络,实现海洋中尺度涡的自动旋转检测。结果实验结果表明,提出的中尺度涡自动检测方法极大改进了水平检测框存在显著的大纵横比导致检测精度低和检测框嵌套和重叠现象。本文方法最优检测精度为90.22%,与水平检测方法相比,精度提升了8%。在印度洋、太平洋、大西洋和赤道海域进行了海洋中尺度涡的旋转检测实证分析,验证了模型具有很好的泛化能力。结论本文通过设计多尺度、多长宽比和多旋转角度实现多尺度旋转锚的生成机制,达到中尺度涡目标旋转检测,有效克服了水平检测框区域冗余和检测框重叠、嵌套现象,显著提升了中尺度涡检测精度。Objective Mesoscale eddy analysis is developed in the field of world’s oceans and marginal seas.The multiscale response mechanism and feedback interaction of mesoscale eddy and ocean phenomena has been promoted through mesoscale eddy generation,growth and extinction,the large scale spatial mesoscale eddy is essential to the issues of transport and distribution of global marine contexts of energy,heat and fresh water in terms of the feature of irregular threedimensional structure and multifaceted dynamics.Therefore,the automatic detection of ocean mesoscale eddy can be used to understand the evolution of ocean mesoscale eddy and the role of ocean mesoscale eddy in material transport and energy transfer.The traditional ocean mesoscale eddy detection methods are mostly adopted based on the physical parameter,flow field geometric feature or both of them.The mesoscale eddies are detected by setting appropriate threshold artificially.The emerging deep learning technology is beneficial to ocean mesoscale eddy detection methods based on deep network model.A classifier is used to classify mesoscale eddy based on manual design and features extraction.The traditional algorithm has good mesoscale eddy detection effect via horizontal bounding box.However,the marine scenario of mesoscale eddy is complicated and ocean mesoscale eddy has the feature of irregular shape,complicated structure and length-width ratio uncertainty and dense distribution.The traditional threshold-dependent detection algorithm has constrained of its rigid and poor generalization ability.The horizontal boundary box methods have redundant horizontal detection region,nested detection box and overlapped issue.Therefore,we propose an automatic detection method of ocean mesoscale eddy based on multiscale rotating anchor mechanism.Method We visualize and normalize the satellite remote sensing sea level height anomaly data.The visual dataset is annotated based on ocean mesoscale eddy understanding and global daily ocean eddy satellite altimeter data.To expand

关 键 词：目标旋转检测 海洋中尺度涡 海平面异常 深度学习 多尺度旋转锚 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]