王峰岩
中国民航大学计算机科学与技术学院 ??天津 ??300300
基金项目:国家自然科学基金(U1833107)，国家科技重大专项(2012ZX03002002)
详细信息
作者简介:杨宏宇：男，1969年生，博士，教授，研究方向为网络信息安全、图像处理
王峰岩：男，1993年生，硕士生，研究方向为网络信息安全、图像处理
通讯作者:杨宏宇 yhyxlx@hotmail.com
中图分类号:TN957.52计量
文章访问数:5292
HTML全文浏览量:1423
PDF下载量:165
被引次数:0
出版历程
收稿日期:2019-02-17
修回日期:2019-06-04
网络出版日期:2019-06-10
刊出日期:2019-10-01
Meteorological Radar Noise Image Semantic Segmentation Method Based on Deep Convolutional Neural Network
Hongyun YANG,,Fengyan WANG
College of Computer Science and Technology, Civil Aviation University of China, Tianjin 300300, China
Funds:The National Natural Science Foundation of China (U1833107), The National Science and Technology Major Project (2012ZX03002002)
摘要
摘要:针对新一代多普勒气象雷达的散射回波图像受非降雨等噪声回波干扰导致精细化短时气象预报准确度降低的问题，该文提出一种基于深度卷积神经网络(DCNN)的气象雷达噪声图像语义分割方法。首先，设计一种深度卷积神经网络模型(DCNNM)，利用MJDATA数据集的训练集数据进行训练，通过前向传播过程提取特征，将图像高维全局语义信息与局部特征细节融合；然后，利用训练误差值反向传播迭代更新网络参数，实现模型的收敛效果最优化；最后，通过该模型对气象雷达图像数据进行分割处理。实验结果表明，该文方法对气象雷达图像的去噪效果较好，与光流法、全卷积网络(FCN)等方法相比，该文方法对气象雷达图像中真实回波和噪声回波的识别准确率高，图像的像素精度较高。
关键词:气象雷达/
深度学习/
图像语义分割/
图像去噪/
卷积神经网络
Abstract:Considering the problem that the scattering echo image of the new generation Doppler meteorological radar is reduced by the noise echoes such as non-rainfall, the accuracy of the refined short-term weather forecast is reduced. A method for semantic segmentation of meteorological radar noise image based on Deep Convolutional Neural Network(DCNN) is proposed. Firstly, a Deep Convolutional Neural Network Model (DCNNM) is designed. The training set data of the MJDATA data set are used for training, and the feature is extracted by the forward propagation process, and the high-dimensional global semantic information of the image is merged with the local feature details. Then, the network parameters are updated by using the training error value back propagation iteration to optimize the convergence effect of the model. Finally, the meteorological radar image data are segmented by the model. The experimental results show that the proposed method has better denoising effect on meteorological radar images, and compared with the optical flow method and the Fully Convolutional Networks (FCN), the method has high recognition accuracy for meteorological radar image real echo and noise echo, and the image pixel precision is high.
Key words:Meteorological radar/
Deep learning/
Image semantic segmentation/
Image denoising/
Convolutional Neural Network(CNN)
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=241255d5-656c-4f74-865a-9345d70b847e
