计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230400041-6.doi: 10.11896/jsjkx.230400041

• 图像处理&多媒体技术 • 上一篇    下一篇

基于多尺度特征的地基云图分类检测算法

孙继飞, 贾克斌   

  1. 北京工业大学信息学部 北京 100024
    先进信息网络北京实验室 北京 100024
  • 发布日期:2024-06-06
  • 通讯作者: 贾克斌(kebinj@bjut.edu.cn)
  • 作者简介:(kidsun@emails.bjut.edu.cn)
  • 基金资助:
    北京市自然科学基金(4212001)

Classification and Detection Algorithm of Ground-based Cloud Images Based on Multi-scale Features

SUN Jifei, JIA Kebin   

  1. Faculty of Information Technology,Beijing University of Technology,Beijing 100024,China
    Beijing Laboratory of Advanced Information Networks,Beijing 100024,China
  • Published:2024-06-06
  • About author:SUN Jifei,born in 1993,master.His main research interests include ground-based cloud images processing and semantic segmentation.
    JIA Kebin,born in 1962,Ph.D,professor,Ph.D supervisor.His main research interest is image and video processing.
  • Supported by:
    Beijing Natural Science Foundation,China(4212001).

PDF (PC)

324

摘要： 地基云的自动识别方法和技术为气象分析中的云状识别和云量估计任务提供了重要的手段和依据。然而,对这两种任务的研究往往独立,互不相干,导致地基云图的分类与分割技术无法有效地结合使用。特别是当云图中出现多类云状时,现有技术难以按不同云类分别划分区域并进行云量计算。为了解决这一问题,提出用基于深度学习的语义分割方法实现对地基云图的按类分割。首先,构建了地基云图语义分割数据集GBCSS,该数据集包含3000幅云图,共计11个类别。在此基础上,提出了一种基于U型神经网络的改进方案UNet-PPM作为地基云图语义分割模型。为了增强网络对云的轮廓特征提取能力,引入了金字塔池化模块。该模块提取并聚合了不同尺度的图像特征,提升了网络获取全局信息的能力。最后,将设计的网络在GBCSS上进行了训练以及评估,其在测试集上达到了91.5%的像素准确率。与U-Net相比,UNet-PPM在像素准确率上有5.4%的提升,表明该网络对云的轮廓特征提取的能力更强,以及语义分割应用在地基云图中的可行性。

关键词: 地基云图, 语义分割, 云图数据集, 全卷积网络, 金字塔池化模块

Abstract: Clouds constantly contribute significantly to climate change in addition to having a short-term impact on local temperatures.To study local cloud details,the ground-based observation is used caused by its ability of cloud image capture in high temporal and spatial resolution.The research on automatic identification of ground-based clouds is primarily focused on two areas:cloud classification and cloud detection.Traditionally,both of them are regarded as separate and unrelated tasks.Cloud classification are independent of the segmentation,and most segmentation techniques focus on binary segmentation.This making it difficult to segment regions by different cloud types when the cloud image contains multiple classes of clouds.To address this problem,this paper proposes a semantic segmentation method based on deep learning for the combination of two tasks.First,it constructs the fround-based cloud image semantic segmentation(GBCSS) dataset,which contains 3000 cloud images with a total of 11 types.All images are resized to a square format of 256×256 pixels.Then,an improved scheme based on U-shaped neural networks is designed as the semantic segmentation model for ground-based cloud images.The pyramid pooling module is combined for extracting and aggregating image features at different scales.This module improves the network’s ability to obtain global information.The developed network UNet-PPM achieves 91.5% pixel accuracy on average on the test set after being trained and assessed on GBCSS.Our suggested enhanced method outperforms the U-Net,Deeplabv3+,DANet and BiSeNetv2 in terms of pixel accuracy.Experiment results show that the pyramid pooling module contributes a lot to extract cloud contour features and restrain the overfitting problem.Our work show the feasibility of semantic segmentation application in cloud image automatic observation.

Key words: Ground-based cloud image, Semantic segmentation, Cloud image dataset, Fully convolutional network, Pyramid pooling module

中图分类号: 

  • TP183
[1]ZHAO C,CHEN Y,LI J,et al.Fifteen-year statistical analysisof cloud characteristics over China using Terra and Aqua Modera-te Resolution Imaging Spectroradiometer observations[J].International Journal of Climatology,2019,39(5):2612-2629.
[2]ZHU B,YANG J,LV W T,et al.Ground-based visible cloudimage classification method based on KNN algorithm[J].Journal of Applied Meteorological Science,2012,23(6):721-728.
[3]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenetclassification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.
[4]ZHU W,CHEN T,HOU B,et al.Classification of ground-based cloud images by improved combined convolutional network[J].Applied Sciences,2022,12(3):1570.
[5]SAITO M,IWABUCHI H.Cloud discrimination from sky images using a clear-sky index[J].Journal of Atmospheric and Oceanic Technology,2016,33(8):1583-1595.
[6]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440.
[7]ZHANG X,JIA K B,LIU J,et al.Segmentation Technology of Ground-Based Cloud Image for Lightweight[J].Measurement & Control Technology,2022,41(9):37-43.
[8]YE L,CAO Z,XIAO Y,et al.Supervised fine-grained cloud detection and recognition in whole-sky images[J].IEEE Transactions on Geoscience and Remote Sensing,2019,57(10):7972-7985.
[9]BANKERT R L.Cloud classification of AVHRR imagery inmaritime regions using a probabilistic neural network[J].Journal of Applied Meteorology and climatology,1994,33(8):909-918.
[10]DEV S,LEE Y H,WINKLER S.Multi-level semantic labeling of sky/cloud images[C]//2015 IEEE International Conference on Image Processing(ICIP).IEEE,2015:636-640.
[11]DEV S,LEE Y H,WINKLER S.Categorization of cloud image patches using an improved texton-based approach[C]//2015 IEEE International Conference on Image Processing(ICIP).IEEE,2015:422-426.
[12]DEV S,LEE Y H,WINKLER S.Color-based segmentation of sky/cloud images from ground-based cameras[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,10(1):231-242.
[13]COHN S A.A new edition of the international cloud atlas[J].WMO Bulletin,Geneva,World Meteorological Organization,2017,66:2-7.
[14]ZHANG J,LIU P,ZHANG F,et al.CloudNet:Ground-basedcloud classification with deep convolutional neural network[J].Geophysical Research Letters,2018,45(16):8665-8672.
[15]ZHUO W,CAO Z,XIAO Y.Cloud classification of ground-based images using texture-structure features[J].Journal of Atmospheric and Oceanic Technology,2014,31(1):79-92.
[16]XIE W,LIU D,YANG M,et al.SegCloud:A novel cloud image segmentation model using a deep convolutional neural network for ground-based all-sky-view camera observation[J].Atmospheric Measurement Techniques,2020,13(4):1953-1961.
[17]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18th International Conference,Munich,Germany.Springer International Publishing,2015:234-241.
[18]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2881-2890.
[19]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).2018:801-818.
[20]FU J,LIU J,TIAN H,et al.Dual attention network for scene segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:3146-3154.
[21]YU C,GAO C,WANG J,et al.Bisenet v2:Bilateral networkwith guided aggregation for real-time semantic segmentation[J].International Journal of Computer Vision,2021,129:3051-3068.
[22]GONG C,WANG D,LI M,et al.Keepaugment:A simple information-preserving data augmentation approach[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:1055-1064.
[23]LIU J W,LIU Y,LUO X L.Semi-Supervised Learning Methods[J].Chinese Journal of Computers,2015,38(8):1592-1617.
[24]CHEN M,DU Y,ZHANG Y,et al.Semi-supervised learningwith multi-head co-training[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:6278-6286.
[25]HEO B,KIM J,YUN S,et al.A comprehensive overhaul of fea-ture distillation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:1921-1930.
[26]LIU Z,LI J,SHEN Z,et al.Learning efficient convolutional networks through network slimming[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2736-2744.
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