杨志坚,陈曦,杨辽,王伟胜,曹强

• 1:中国科学院新疆生态与地理研究所
• 2:中国科学院大学
• 3:辽宁师范大学海洋经济与可持续发展研究中心

摘要(Abstract)：

针对传统耕地提取方法人工干预多、提取速度慢、成本高,不适用于大规模耕地提取等问题,选取时间序列Sentinel-2数据,基于时序光谱特征的耕地自动识别方法对玛纳斯县典型耕地区域进行耕地提取,并比较了不同样本特征对耕地提取精度的影响。结果表明:采用该方法总体分类精度、Kappa系数、耕地类型的用户精度分别达到了95.37%、0.942 3和97.04%,比采用时间序列NDVI和单时期影像样本特征总体精度分别提高4.02%和5.69%。研究结果为进一步利用中高分辨率遥感数据和深度学习方法对耕地进行信息提取和典型地物分类提供了新思路。

关键词(KeyWords)： 时序光谱图;卷积神经网络;哨兵-2数据;耕地提取

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划项目(2017YFB0504204)

作者(Author): 杨志坚,陈曦,杨辽,王伟胜,曹强

DOI: 10.16251/j.cnki.1009-2307.2020.11.010

参考文献(References)：

• [1] 郑沃林,殷梅华,吴建辉.中国耕地保护研究的回顾与进展[J].世界地理研究,2016,25(5):69-80.(ZHENG Wolin,YIN Meihua,WU Jianhui.Review and progress of farmland projection in china[J].World Regional Studies,2016,25(5):69-80.)
• [2] 于利峰,乌兰吐雅,乌云德吉,等.基于纹理特征与MODIS-NDVI时间序列的耕地面积提取研究[J].中国农业资源与区划,2018,39(11):169-177.(YU Lifeng,WULAN Tuya,WUYun Deji,el al.Study on extraction of arable land area based on texture features and MODIS-NDVI time series[J].China Journal of Agricultural Resources and Regional Planing,2018,39(11):169-177.)
• [3] 葛向东,彭补拙,黄贤金,等.耕地总量动态平衡的监测和预警研究[J].自然资源学报,2002(1):35-41.(GE Xiangdong,PENG Buzhuo,HUANG Xianjin,el al.A research into monitoring and early-waining of dynamic balance maintenance of total farmland[J].Journal of Natural Resources,2002(1):35-41.)
• [4] 李昌俊,黄河,李伟.基于支持向量机的农业遥感图像耕地提取技术研究[J].仪表技术,2018(11):5-8,48.(LI Changjun,HUANG He,LI Wei.Research on agricultural remote sensing image cultivated land extraction technology based on support vector machine[J].Instrumentation Technology,2018(11):5-8,48.)
• [5] 徐超,詹金瑞,潘耀忠,等.基于多时相TM图像的耕地信息提取[J].国土资源遥感,2013,25(4):166-173.(XU Chao,ZHAN Jinrui,PAN Yaozhong,el al.Extraction of cropland information based on multi-temporal TM images[J].Remote Sensing for Land & Resources,2013,25(4):166-173.)
• [6] TEWKESBURY A P,COMBER A J,TATE N J,et al.A critical synthesis of remotely sensed optical image change detection techniques[J].Remote Sensing of Environment,2015,160:1-14.
• [7] DRUSCH M,DEL BELLO U,CARLIERS,et al.Sentinel-2:ESAs optical high-resolution mission for GMES operational services[J].Remote Sensing of Environment,2012,120:25-36.
• [8] 方灿莹,王琳,徐涵.不同植被红边指数在城市草地健康判别中的对比研究[J].地球信息科学学报,2017,19(10):1382-1392.(FANG Canying,WANG Lin,XU Han.A comparative study of different red edge indices for remote sensing detection of urban grassland health status[J].Journal of Geo-Information Science,2017,19(10):1382-1392.)
• [9] 黄双燕,杨辽,陈曦,等.机器学习法的干旱区典型农作物分类[J].光谱学与光谱分析,2018,38(10):3169-3176.(HUANG Shuangyan,YANG Liao,CHEN Xi,et al.Study of trpical Arid crops classification based on machine learning[J].Spectroscopy and Spectral Analysis,2018,38(10):3169-3176.)
• [10] ESA.Sentinel-2 user handbook[EB/OL].(2015-07-24)[2017-04-08].https://sentinels.copernicus.eu/web/senti-nel/home.
• [11] BENGIO Y,COURVILE A,VINCEN P.Representation learning:a review and new perspectives[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(8):1798-1828.
• [12] TRUONG T D,NGUYEN V T,TRAN M T.Lightweight deep convolutional network for tiny object recognition[M].[S.l.:s.n.],2008:675-682.
• [13] 宫浩,张秀再,胡敬锋.一种基于深度学习的遥感图像分类及农田识别方法[J].现代电子技术,2019(8):179-182,186.(GONG Hao,ZHANG Xiuzai,HU Jingfeng.A remote sensing image classification and farmland identification method based on deep learning[J].Modern Electronics Technique,2019(8):179-182,186.)
• [14] 王翠娥,李香林,崔冬华.复杂网络数据流的入侵数据检测方法仿真[J].计算机仿真,2015,32(12):272-275.(WANG Cuie,LI Xianglin,CUI Donghua.Complex network simultion data flow of spatial data detection method[J].Computer Simulaion,2015,32(12):272-275.)
• [15] HINTON G E,SRIVASTAVA N,KRIZHEVSKY A,et al.Improving neural networks by preventing co-adaptation of feature detectors[J].Comput Science,2012,3(4):212-223.
• [16] SRIVASTAVA N,HINTON G,KRIZHEVSKY,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(1):1929-1958.
• [17] CONGALTON R G.A review of assessing the accuracy of classifica-tions of remotely sensed data[J].Remote Sensing of Environment,1991,37:35-46.
• [18] 戴建国,张国顺,郭鹏,等.基于无人机遥感可见光影像的北疆主要农作物分类方法[J].农业工程学报,2018,34(18):122-129.(DAI Jianguo,ZHANG Guoshun,GUO Peng,et al.Classification method of main crops in northern Xinjiang based on UAV visible waveband images[J].Transactions of the Chinese Society of Agricultural Engineeing,2018,34(18):122-129.)
• [19] 李丹,梁欣,孙丽娜,等.基于多时相遥感影像的耕地利用信息提取研究[J].现代测绘,2018,41(4):21-24.(LI Dan,LIANG Xin,SUN Lina,et al.Study on extraction of cultivated land information based on multi-temporal remote sensing images[J].Modern Surveying and Mapping,2018,41(4):21-24.)
• [20] 赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.(ZHAO Yingshi.Principles and methods of remote sensing application analysis[M].Beijing:Science Press,2003.)