PDF(552 KB)
基于 GF－1 遥感影像的荒漠区耕地分类与提取方法
马永建, 汪传建, 赵庆展, 任媛媛, 田文忠
PDF(552 KB)
PDF(552 KB)
基于 GF－1 遥感影像的荒漠区耕地分类与提取方法
Study on extraction of cultivated land in desert area with GF－1 remote sensing image based on U－Net model
As a kind of strategic natural resources,cultivated land is the material basis and important premise to ensure the safety of food production in China. The ecological environment of oasis cultivated land in desert areas is fragile and vulnerable to wind and sand erosion,so it’s important to make a continuous and accurate monitoring of cultivated land in this area. This paper is based on deep learning algorithm,using GF-1 remote sensing data to extract cultivated land and its category information.In order to make full use of the phenological characteristics of the study area,combined with the remote sensing images in winter and summer,the NDVI value of vegetation index and the energy value of gray-scale co-occurrence matrix of texture feature are taken as the feature bands,and the cultivated land is classified and extracted based on the u-net model,mainly including three types of cultivated land ( cotton field) ,fruit forest cultivated land and wasteland.The results shows that the recognition rate of farmland can reach 90. 83% only using summer images.Adding winter image,vegetation index and texture feature band can effectively improve the recognition effect of the model.The total recognition rate is 88. 39% and 79. 51% respectively,which is 4. 67% and 6. 11% higher than the traditional method.At the same time,compared with support vector machine and random forest classifier,this method can reduce the“salt and pepper noise”between the same crop and avoid large-scale farmland classification errors.This method can provide reference for fast identification and monitoring of oasis cultivated land in desert area.
深度学习 / 耕地提取 / GF-1 卫星 / 高分辨率遥感 / U-Net 网络 {{custom_keyword}} /
deep learning / farmland extraction / GF-1 satellite / high-resolution remote sensing / U-Net {{custom_keyword}} /
[1] 姚成胜,滕毅,黄琳.中国粮食安全评价指标体系构建 及实证分析[J].农业工程学报,2015,31( 4) : 1-10. YAO C S,TENG Y,HANG L.Evaluation index system construction and empirical analysis on food[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31 ( 4) : 1-10.
[2] 刘彦文,刘成武,何宗宜,等.基于像元尺度耕地质量局 部空间自相关的基本农田划定[J]. 农业机械学报, 2019,50( 5) : 260-268. LIU Y W,LIU C W,HE Z Y,Zhou X.Delineation of basic farmland based on local spatial autocorrelation analysis of cultivated land quality in pixel scale[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50 ( 5) : 260-268.
[3] CHENG Y X,HUANG J F,HAN Z L,et al.Cold damage risk assessment of double cropping rice in Hunan,China[J].Journal of Integrative Agriculture,2013,12( 2) : 352- 363.
[4] 胡汝骥,陈曦,姜逢清,等.人类活动对亚洲中部水环境 安全的威胁[J].干旱区研究,2011,28( 2) : 189-197. HU R J,CHEN X,JIANG F Q,et al.Threat of human activities to hydrological regime in central Asia[J]. Arid Zone Research,2011,28( 2) : 189-197.
[5] 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 S Y,YANG L,CHEN X,et al. Study of typical arid crops classification based on machine learning[J]. Spectroscopy and Spectral Analysis,2018 38( 10) : 3169- 3176.
[6] 左丽君,张增祥,董婷婷,等.MODIS/NDVI 和 MODIS/ EVI 在耕地信息提取中的应用及对比分析[J].农业工 程学报,2008,24( 3) : 167-172. ZUO L J,ZHANG Z X,DONG T T,et al. Application of MODIS/NDVI and MODIS EVI to extracting the information of cultivated land and comparison analysis[J].Transactions of the Chinese Society of Agricultural Engineering,2008,24 ( 3) : 167-172.
[7] 孙丽,吴全,张松岭,等.小地物比例提取在河北耕地遥 感调查中的应用研究[J]. 农 业 工 程 学 报,2006,22 ( 2) : 79-82. SUN L,WU Q,ZHANG S L,et al.Estimation of area ratios of small features in crop area obtained by remote sensing technique in Hebei Province[J].Transactions of the Chinese Society of Agricultural Engineering,2006,22( 2) : 79 -82.
[8] 陈杰,邓敏,肖鹏峰,等.粗糙集高分辨率遥感影像面向 对象分类[J].遥感学报,2010,14( 6) : 1139-1155 CHEN J,DENG M,XIAO P F,et al. Rough set theory based object-oriented classification of high resolution remotely sensed imagery[J]. Journal of Remote Sensing, 2010,14( 6) : 1139-1155.
[9] 陈杰,陈铁桥,梅小明,等.基于最优尺度选择的高分辨 率遥感影像丘陵农田提取[J].农业工程学报,2014,30 ( 5) : 99-107. CHEN J,CHEN T Q,MEI X M,et al.Hilly farmland extraction from high resolution remote sensing imagery based on optimal scale selection[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30 ( 5) : 99 - 107.
[10] 鲁恒,付萧,贺一楠,等.基于迁移学习的无人机影像耕 地信息提取方法[J].农业机械学报,2015,46( 12) : 274 -279 LU H,FU X,HE Y N,et al. Cultivated land information extraction from high resolution UAV images based on transfer learning[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46( 12) : 274-279.
[11] OZDARICI A,TURKER M. Field-based classification of different resolution images and the filtering effects on the accuracies[C]/ / International Conference on Recent Advances in Space Technologies.IEEE Xplore,2007
[12] SLAVKOVIKJ V,VERSTOCKT S,DE N W,et al.Hyperspectral image classification with convolutional neural networks[C]/ /The 23rd ACM International Conference. ACM,2015.
[13] ZHAO W,DU S.Spectral-spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54( 8) : 4544-4554.
[14] RONNEBERGER O,FISCHER P,BROX T.U-Net: Convolutional networks for biomedical image segmentation[C]/ / International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer International Publishing,2015.
[15] 刘浩,骆剑承,黄波,等.基于特征压缩激活 Unet 网络 的建筑物提取[J].地球信息科学学报,2019,21( 11) : 1779-1789. LIU H,LUO J C,HUANG B,et al.2019 Building extraction based on SE-Unet[J].Journal of Geo-Information Science,2019,21( 11) : 1779-1789.
[16] 张宏鸣,王斌,韩文霆,等.基于全卷积神经网络的灌区 无人机正射影像渠系提取[J].农业机械学报,2019,50 ( 6) : 241-248. ZHANG H M,WANG B,HAN W T,et al.Extraction of Irrigation Networks in Irrigation Area of UAV Orthophotos Based on Fully Convolutional Networks[J]. Transactions of the Chinese Society for Agricultural Machinery,2019, 50( 6) : 241-248.
[17] 李越帅,郑宏伟,罗格平,等.集成 U-Net 方法的无人机 影像胡杨树冠提取和计数[J].遥感技术与应用,2019, 34( 5) : 939-949. LI Y S,ZHENG H W,LUO G P,et al. Extraction and Counting of Populus Euphratica Crown Using UAV Images Integrated with U-Net Method[J].Remote Sensing Technology and Application,2019,34( 5) : 939-949.
[18] RYDBERG A,BORGEFORS G. Integrated method for boundary delineation of agricultural fields in multispectral satellite images[J].IEEE Transactions on Geoscience and Remote Sensing,2001,39( 11) : 2514-2520.
[19] 田振坤,傅莺莺,刘素红,等.基于无人机低空遥感的农 作物快速分类方法[J].农业工程学报,2013,29( 7) : 109-116. TIAN Z K,FU Y Y,LIU S H,et al.Rapid crops classification based on UAV low-altitude remote sensing[J].Transactions of the Chinese Society of Agricultural Engineering,2013,29 ( 7) : 109-116.
[20] 李明,黄愉淇,李绪孟,等.基于无人机遥感影像的水稻 种植信息提取[J].农业工程学报,2018,34( 4) : 108- 114. LI M,HUANG Y Q,LI X M,et al.Extraction of rice planting information based on remote sensing image from UAV[J].Transactions of the Chinese Society of Agricultural Engineering,2018,34( 4) : 108-114.
[21] SIMON J,MICHAL D,DAVID V,et al. The one hundred layers Tiramisu: Fully convolutional DenseNets for semantic segmentation[C]/ / IEEE Conference on Computer Vision and Pattern Recognition Workshops ( CVPRW) . IEEE,2016.
[22] KRIZHEVSKY A,SUTSKEVER I,HINTON G. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012,25( 2) .
总访问:63544,今日访问:256, 当前在线:7
/
| 〈 |
|
〉 |
