机器学习在遥感影像分类中的应用

高昂; 唐世浩; 肖萌; 郑伟

doi:10.3981/j.issn.1000-7857.2021.15.007

PDF(1527 KB)

科技导报 ›› 2021, Vol. 39 ›› Issue (15) : 67-74. DOI: 10.3981/j.issn.1000-7857.2021.15.007

专题：气象卫星应用于气象灾害监测预警

机器学习在遥感影像分类中的应用

作者信息 -

国家卫星气象中心, 北京 100081

作者简介:

高昂,博士,研究方向为机器学习,电子信箱:gaoang@cma.gov.cn

Application of machine learning in remote sensing image classification

Author information -

National Satellite Meteorological Center, Beijing 100081, China

摘要

概述了机器学习的主要方法及其在遥感影像的主要应用方向，涵盖环境生态遥感中机器学习技术的研究、应用情况及近年来的新进展。通过使用深度学习对FY-3C气象卫星资料进行积雪检测的应用实例，说明深度学习模型可以利用大数据的优势不断提高检测精度，在某些指标中取得了更优于传统机器学习的精度，可解决传统机器学习难以解决的一些问题，从而带动遥感应用模式的创新。

Abstract

This paper summarizes the main methods of machine learning and its main application direction in remote sensing image. It covers the research and application of machine learning technology in environmental ecological remote sensing, and the new progress in recent years. Through the application of deep learning to snow detection of FY-3C meteorological satellite data, it is shown that the deep learning model can improve the detection accuracy by means of big data advantages, and has achieved better precision than traditional machine learning in some indexes, thus solving some problems that are difficult to solve using traditional machine learning method, and driving the innovation of remote sensing application mode.

导出引用

高昂, 唐世浩, 肖萌, 郑伟. 机器学习在遥感影像分类中的应用[J]. 科技导报, 2021, 39(15): 67-74 https://doi.org/10.3981/j.issn.1000-7857.2021.15.007

GAO Ang, TANG Shihao, XIAO Meng, ZHENG Wei. Application of machine learning in remote sensing image classification[J]. Science & Technology Review, 2021, 39(15): 67-74 https://doi.org/10.3981/j.issn.1000-7857.2021.15.007

参考文献

[1] 周志华. 机器学习[M]. 清华大学出版社, 2016.
[2] Mjolsness E, DeCoste D. Machine learning for science:State of the art and future prospects[J]. Science, 2001, 293(5537):2051-2055.
[3] 刘颖. 基于半监督集成支持向量机的土地覆盖遥感分类方法研究[D]. 中国科学院研究生院(东北地理与农业生态研究所), 2013.
[4] 杨晨. 基于机器学习的土地覆盖遥感信息提取方法研究[D]. 吉林大学, 2010.
[5] Géron A. Hands-on machine learning with scikit-learn, keras, and tensorFlow:Concepts, tools, and techniques to build intelligent systems[M]. O'Reilly Media, 2019.
[6] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
[7] 刘毅, 杜培军, 郑辉, et al. 基于随机森林的国产小卫星遥感影像分类研究[J]. 测绘科学, 2012, 37(4):194-196.
[8] Lowe B, Kulkarni A. Multispectral image analysis using random forest[J]. 2015.
[9] Rodriguez-Galiano VF, Ghimire B, Rogan J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67:93-104.
[10] 刘海娟. 基于RF模型的高分辨率遥感影像分类评价[J]. 南京林业大学学报:自然科学版, 2015, (39):99-103.
[11] Ghimire B, Rogan J, Miller J. Contextual land-cover classification:Incorporating spatial dependence in landcover classification models using random forests and the Getis statistic[J]. Remote Sensing Letters, 2010, 1(1):45-54.
[12] Salas EAL, Boykin KG, Valdez R. Multispectral and texture feature application in image-object analysis of summer vegetation in Eastern Tajikistan Pamirs[J]. Remote Sensing, 2016, 8(1):78.
[13] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[14] Joachims T. Text categorization with support vector machines:Learning with many relevant features[C]. Dortmund Germany:Springer, 1998:137-142.
[15] Vapnik V. The nature of statistical learning theory[M]. Springer Science & Business Media, 2013.
[16] Vapnik VN. An overview of statistical learning theory[J]. IEEE transactions on neural networks, 1999, 10(5):988-999.
[17] 卢伟, 文鸿雁, 李淑. 基于SVM的遥感影像空间特征提取和分类研究[J]. 山西建筑, 2009, 35(5):10-12.
[18] 张耀波, 张迁. 基于SVM的遥感影像的分类[J]. 地理空间信息, 2005, (4):24-26.
[19] Kohonen T. Adaptive, associative, and self-organizing functions in neural computing[J]. Applied optics, 1987, 26(23):4910-4918.
[20] Kanellopoulos I, Wilkinson GG. Strategies and best practice for neural network image classification[J]. International Journal of Remote Sensing, 1997, 18(4):711-725.
[21] 陈岩, 李洋洋, 余乐, 等. 基于卷积神经网络的手写体数字识别系统[J]. 微电子学与计算机, 2018, 35(2):71-74.
[22] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25:1097-1105.
[23] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[24] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. 2014, arXiv:14091556.
[25] Yang F, Jin L, Yang W, et al. Handwritten/printed receipt classification using attention-based convolutional neural network[C]. IEEE, 2016:384-389.
[26] 郑益勤, 杨晓峰, 李紫薇. 深度学习的静止卫星图像海上强对流云团识别[J]. 遥感学报, 2020, 24(1):97-106.
[27] Chen Y, Lin Z, Zhao X, et al. Deep learning-based classification of hyperspectral data[J]. IEEE Journal of Selected topics in applied earth observations and remote sensing, 2014, 7(6):2094-2107.
[28] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[29] LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series[J]. The Handbook of Brain Theory and Neural Networks, 1995, 3361(10):1995.
[30] Badrinarayanan V, Kendall A, Cipolla R. Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495.
[31] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]. 2015:3431-3440.
[32] Ronneberger O, Fischer P, Brox T. U-net:Convolutional networks for biomedical image segmentation[C]. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, 2015:234-241.
[33] Lee C-Y, Gallagher P, Tu Z. Generalizing pooling functions in CNNs:Mixed, gated, and tree[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4):863-875.
[34] Klambauer G, Unterthiner T, Mayr A, et al. Self-normalizing neural networks[C]. 31st Conference on Neural Information Processing Systems (NIPS 2017):Long Beach, CA, USA, 2017:972-981.
[35] 李金洪. 深度学习之TensorFlow:入门、原理与进阶实战[M]. 北京:机械工业出版社, 2018.
[36] 李爱勤, 王环东, 王静怡, 等. 高分辨率遥感影像中云和似云目标的自动区分[J]. 测绘通报, 2017, (6):31-35.
[37] Rossow WB, Garder LC. Cloud detection using satellite measurements of infrared and visible radiances for ISCCP[J]. Journal of Climate, 1993, 6(12):2341-2369.
[38] Taylor VR, Stowe LL. Reflectance characteristics of uniform earth and cloud surfaces derived from NIMBUS 7 ERB[J]. Journal of Geophysical Research:Atmospheres, 1984, 89(D4):4987-4996.
[39] Di Vittorio A V, Emery W J. An automated, dynamic threshold cloud-masking algorithm for daytime AVHRR images over land[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(8):1682-1694.
[40] 武艳, 银燕, 师春香, 等. 基于动态阈值法的NOAA系列卫星云检测结果检验[J]. 高原气象, 2012, 31(3):745-751.
[41] Dybbroe A, Karlsson K-G, Thoss A. NWCSAF AVHRR cloud detection and analysis using dynamic thresholds and radiative transfer modeling. part I:Algorithm description[J]. Journal of Applied Meteorology and Climatology, 2005, 44(1):39-54.
[42] Poli G, Adembri G, Gherardelli M, et al. Dynamic threshold cloud detection algorithm improvement for AVHRR and SEVIRI images[C]//2010 IEEE International Geoscience and Remote Sensing Symposium. Honolulu, HI, USA, IEEE, 2010:4146-4149.
[43] 刘健. 中国区域云特性分析及在FY-2云检测中的应用[J]. 应用气象学报, 2009, 20(6):673-681.
[44] 刘健. FY-2云检测中动态阈值提取技术改进方法研究[J]. 红外与毫米波学报, 2010, 29(4):288-292.
[45] 刘希, 许健民, 杜秉玉. 用双通道动态阈值对GMS-5图像进行自动云检测[J]. 应用气象学报, 2005, (4):434-444.
[46] 杨铁利, 何全军. MODIS数据的云检测处理[J]. 鞍山科技大学学报, 2006, (2):162-166.
[47] 李娅, 郭建侠, 曹云昌, 等. FY-2G云量产品与地面观测云量对比分析[J]. 高原气象, 2018, 37(2):514-523.
[48] 裔传祥, 辛晓洲, 胡继超, 等. 基于GF-4数据分析低分辨率卫星云检测尺度误差对下行辐射计算的影响[J]. 地球科学进展, 2018, 33(4):425-434.
[49] 刘炼烨, 兰明才, 朱歆炜, 等. FY-2G卫星两种云订正产品在湖南的对比分析[J]. 暴雨灾害, 2017, 36(2):164-170.
[50] 瞿建华, 鄢俊洁, 薛娟, 等. 基于深度学习的FY3D/MERSI和EOS/MODIS云检测模型研究[J]. 气象与环境学报, 2019, 35(3):87-93.
[51] 徐启恒, 黄滢冰, 陈洋. 结合超像素和卷积神经网络的国产高分辨率遥感影像云检测方法[J]. 测绘通报, 2019, (1):50-55.
[52] 陈洋, 范荣双, 王竞雪, 等. 基于深度学习的资源三号卫星遥感影像云检测方法[J]. 光学学报, 2018, 38(1):362-367.
[53] Burges C J. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[54] 康晓光, 孙龙祥. 基于人工神经网络的云自动检测算法[J]. 解放军理工大学自然科学版, 2005, (5):102-106.
[55] Zhou Z, Siddiquee MMR, Tajbakhsh N, et al. Unet++:A nested u-net architecture for medical image segmentation[M]//Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, 2018:3-11.