基于多尺度镶嵌的Mask R-CNN台风中心定位  

Location of Typhoon Center Based on Multi-Scale Mosaic Mask R-CNN

作　　者：郑宗生[1] 赵家惠 卢鹏[1] 邹国良[1] 王振华[1] Zheng Zongsheng;Zhao Jiahui;Lu Peng;Zou Guoliang;Wang Zhenhua(College of Information Technology,Shanghai Ocean University,Shanghai 201306,China)

机构地区：[1]上海海洋大学信息学院,上海201306

出　　处：《激光与光电子学进展》2023年第10期111-119,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金项目(41671431);上海市科委市地方能力建设项目(19050502100);国家海洋局数字海洋科学技术重点实验室开放基金项目(B201801034);上海海洋大学科技发展专项基金(A2-2006-20-200211)。

摘　　要：准确自动检测台风风眼位置可为台风预报与监测研究提供先验信息,以减少灾害损失。由于台风形态结构的多变性,其中心自动定位仍存在一定的困难。本研究利用台风卫星云图,提出一种基于多尺度镶嵌的R-CNN台风风眼检测方法。收集日本气象厅发布的1981—2017年5000多张台风卫星云图,利用图像数据中风眼眼壁轮廓曲线及内外明暗差别清晰明显的特点对图中风眼进行分割标注。通过台风风眼半径多尺度估算算法,将原始图像划分为多尺度台风云图,整合训练集和测试集。借助多尺度图像镶嵌、超参数选择和多条件测试分析,构建利用多尺度Mask R-CNN模型检测分割台风风眼的总体算法框架,开展多尺度对比实验。在自建标定数据集中,台风风眼的识别准确率最高达到92.63%、最低为88.36%,平均每张图片的检测时间最少为0.043 s,均方误差最小达到2154,平均交并比最大为0.9454。实验结果表明,所提多尺度镶嵌数据增强方法在大中规模尺度融合时效果最好、中小尺度较差,与现有主要数据增强方法相比,能更有效地提升神经网络准确率。整体检测模型在台风中心定位中的综合效率优于其他深度学习定位方法。Accurate automatic detection of typhoon eye position can provide a priori information for typhoon forecast and monitoring research to reduce disaster loss.Due to the variability of typhoon morphology,it is still difficult to locate typhoon center automatically.In this paper,a RCNN method for typhoon eye detection based on multiscale mosaic is proposed with typhoon satellite cloud images.More than 5000 typhoon satellite cloud images released by Japan Meteorological Agency from 1981 to 2017 are collected.The typhoon eye in the image based on the contour curves of the eye wall and the clear brightness difference between the inside and outside of the typhoon eye is segmented.The original image is divided into multiscale typhoon cloud images by multiscale estimation algorithm of typhoon eye radius,and the training set and test set are integrated.With the help of multiscale image mosaic,hyperparameter selection and multicondition test analysis,the overall algorithm framework of detecting and segmental typhoon eye using multiscale Mask RCNN model is constructed,and multiscale comparison experiments are carried out.In the selfbuilt calibration dataset,the identification accuracy of typhoon eye is from 88.36%up to 92.63%.The average detection time of each image is at least 0.043 s,the minimum mean square error is 2154,and the maximum average crossover ratio is 0.9454.The experimental results show that the proposed multiscale mosaic data augmentation method has the best effect in large and medium scale scale fusion,but is poor in small and medium scale fusion.Compared with the existing main data augmentation methods,it can improve the accuracy of neural network more effectively.The comprehensive efficiency of the whole detection model in typhoon center location is better than other deep learning localization methods.

关 键 词：图像处理 台风风眼 目标检测 实例分割 卫星云图 数据增强 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]