计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 250300044-7.doi: 10.11896/jsjkx.250300044

• 计算机图形学&多媒体 • 上一篇    下一篇

基于深度学习的云南40米射电望远镜的RFI抑制

罗鑫1, 梁波2   

  1. 1 昆明理工大学计算机重点实验室 昆明 650100
    2 昆明理工大学信息工程与自动化学院 昆明 650100
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 罗鑫(749853144@qq.com)
  • 基金资助:
    国家自然科学基金(12063003)

RFI Suppression of the Yunnan 40-meter Radio Telescope Based on Deep Learning

LUO Xin1, LIANG Bo2   

  1. 1 Key Laboratory of Computer,Kunming University of Science and Technology,Kunming 650100,China
    2 School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650100,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    National Natural Science Foundation of China(12063003).

PDF (PC)

11

摘要： 在射电天文中射频干扰(Radio Frequency Interference,RFI)是指所有会干扰射电望远镜接收到微弱天文信号的现象,对天文信号的观测和研究产生严重影响。目前的抑制方法包括人工标记方法、信号处理方法、机器学习和深度学习方法。因此,提出了一种基于DeepLabV3+改进的深度学习神经网络模型,旨在检测天文数据中的RFI。利用云南天文台观测的真实RFI观测数据对模型进行训练,并充分利用卷积神经网络提取图像特征的能力,以便模型能够更好地学习RFI的特征,从而实现更精确的RFI检测。采用模型对图像进行识别,通过估计每个数据点属于RFI的概率,并使用训练好的模型来判断RFI的存在与否。当某个数据点被模型预测为RFI,将其标记为干扰部分,否则标记为非干扰部分,从而实现对图像中带有RFI部分的标记并抑制。实验结果表明,所提出的方法在F1分数、Accuracy和MIoU方面表现出令人满意的水平。与此同时,将所提出的模型与传统的深度学习模型进行了比较,且进行消融实验,以进一步验证其性能优势。

关键词: 射频干扰, 深度学习, 图像处理, 射电天文, 干扰抑制

Abstract: In Radio astronomy,RFI refers to all phenomena that interfere with the weak astronomical signals received by radio telescopes and have a significant impact on the observation and study of astronomical signals.The existing suppression methods at present,such as manual labeling methods,signal processing methods,machine learning and deep learning methods.This paper proposes an improved deep learning neural network model based on DeepLabV3+,aiming to detect RFI in astronomical data.It trains the model using the real RFI observation data observed by the Yunnan Observatory and fully utilizes the ability of the convolutional neural network to extract image features,so that the model can better learn the features of RFI and thereby achieve more accurate RFI detection.It adopts the model to recognize the image.By estimating the probability that each data point belongs to RFI and using the trained model to determine whether RFI exists or not.When a certain data point is predicted as RFI by the model,we mark it as the interfering part;otherwise,we mark it as the non-interfering part,thereby achieving the marking and suppression of the part with RFI in the image.The experimental results show that the proposed method demonstrates a satisfactory level in terms of F1 score,Accuracy and MIoU.Meanwhile,the proposed model is compared with the traditional deep lear-ning model,and ablation experiments are conducted to further verify its performance advantages.

Key words: RFI, Deep learning, Image processing, Radio astronomy, Interference suppression

中图分类号: 

  • TP391.9
[1]AKERET J,CHANG C,LUCCHI A,et al.Radio frequency interference mitigation using deep convolutional neural networks [J].Astronomy and Computing,2017,18:35-39.
[2]AN T.RFI Mitigation in Radio Astronomy:A Review [J].Acta Astronomica Sinica,2017,58:43-52.
[3]ZHU S,WANG Z,WANG M,et al.A Study on RFI Detection and Mitigation Techniques [J].Astronomical Research & Technology,2017,14(3):297-306.
[4]KOCZ J,BRIGGS F H,REYNOLDS J.Spatial Filtering for Radio Frequency Interference Mitigation [J].The Astronomical Journal,2010,140(6):2086-2094.
[5]OFFRINGA A R,DE BRUYN A G,BIELH M,et al.The LOFAR RFI Mitigation Pipeline and Its Applications [J].Monthly Notices of the Royal Astronomical Society,2010,405(1):155-165.
[6]FRIDMAN P,BANNIKOV D.A Method for RFI Mitigation in Pulsar Observations [J].Astronomy & Astrophysics,2001,378:327-332.
[7]ZHAO J,ZOU X,WENG F.Principal Component Analysis for RFI Mitigation in Microwave Radiometry [J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4830-4839.
[8]DAI C,ZUO S F,LIU W,et al.A Comparative Study of RFI Mitigation Algorithms [C]//Astronomical Data Analysis Software and Systems XXVII.2019:71-78.
[9]CZECH D,MISHRA A,INGGS M.A Support Vector Machine Approach for RFI Classification in Radio Astronomy [J].Radio Science,2017,52(7):841-852.
[10]HE K,GKIOXARI G,DOLLÁR P,et al.Mask R-CNN [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):386-397.
[11]BADRINARAYANAN V,KENDALL A,CIPOLLA R.Seg-Net:A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[12]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-Time Object Detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:779-788.
[13]AKERET J,CHANG C,LUCCHI A.Refregier:An RFI Mitigation Tool Based on Deep Learning [J].Astronomy and Computing,2017,18:35-39.
[14]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot MultiBox Detector [C]//Computer Vision－ECCV 2016.Springer,2016:21-37.
[15]CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking Atrous Convolution for Semantic Image Segmentation [J].ar-Xiv:1706.05587,2017.
[16]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [C]//Proceedings of the European Conference on Computer Vision(ECCV).Springer,2018:801-818.
[17]XIA X,XU C,NAN B.U-Net Based RFI Detection in Radio Astronomical Images [C]//2017 2nd International Conference on Image,Vision and Computing(ICIVC).IEEE,2017:124-128.
[18]HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[19]SIMONYAN K,ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition [J].arXiv:1409.1556,2014.
[20]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[21]CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs [J].arXiv:1412.7062,2014.
[22]CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:Semantic Image Segmentation with Deep Convolutional Nets,Atrous Convolution,and Fully Connected CRFs [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发