浏览全部资源
扫码关注微信
纸质出版日期： 2020-05-07 ，
扫 描 看 全 文
宋德娟,张承明,杨晓霞,李峰,韩颖娟,高帅,董海燕.2020.高分二号遥感影像提取冬小麦空间分布.遥感学报,24(5): 596-608
Song D J,Zhang C M,Yang X X,Li F,Han Y J,Gao S and Dong H Y. 2020. Extracting winter wheat spatial distribution information from GF-2 image. Journal of Remote Sensing（Chinese），24(5): 596-608[DOI：10.11834/jrs.20208285]
精细的农作物空间分布数据对于资源、环境、生态、气候变化和粮食安全问题均具有重要的意义，卷积神经网络已经成为从遥感影像中提取农作物空间分布数据的主要方法，但提取结果中的种植区域边缘往往比较粗糙。本文以高分二号遥感影像为数据源，选择冬小麦为提取目标，利用RefineNet模型和最大后验概率模型构建冬小麦遥感提取模型WWRSE（Winter Wheat Remote Sensing Extraction），获取精细的冬小麦空间分布数据。WWRSE模型利用RefineNet网络提取像素的语义特征，使用改进的SoftMax模型生成像素的类别概率向量；以类别概率向量的最大分量与次大分量的差值作为置信度，根据置信度将类别概率向量分为可信和不可信两组，可信组直接使用最大分量对应的类别标签作为相应像素的分类结果；结合最大后验概率模型确定不可信组像素的分类结果。利用随机梯度法对WWRSE模型进行训练。选择SegNet、DeepLab、RefineNet作为对比模型进行实验，WWRSE提取结果的精度为92.9%，比SegNet提高了13.8%，比DeepLab提高了10.9%，比RefineNet提高了8.6%。实验结果表明WWRSE模型在提取冬小麦空间分布数据方面具有一定的优势。WWRSE模型提取的结果能够为大范围冬小麦种植面积统计提供依据。
Winter wheat is one of the main food crops in China. The accurate spatial distribution information of winter wheat is crucial for yield estimation and food security. However
existing methods for extracting the spatial distribution information of winter wheat using a full convolutional neural network ignore the remote sensing imagery characteristics. The influence of differences among probabilities in the coded class probability vector on the judgment of pixel class attribution can lead to misclassification or missing points at the edge
which can affect the accuracy of the result. In this study
the RefineNet model is coupled with maximum a posteriori probability (MAP)
and the WWRSE(Winter Wheat Remote Sensing Extraction) model is developed to create a method for extracting the spatial distribution information of winter wheat from a Gaofen-2 remote sensing image.
The WWRSE uses the convolution RefineNet network structure to extract pixel features. An improved SOFTMAX model is used to obtain the pixel category probability vector. With the winter wheat category probability value and other categories as a poor probability vector
differences can be divided into small pixels and differences among large pixels according to the category probability vector. For large differences among pixels
the biggest probability category can be used directly as the pixel category. Small differences among pixels can be combined with the MAP model to determine the type of each pixel. Next
the model is trained using the stochastic gradient method
and the spatial distribution information of winter wheat is extracted from the remote sensing image using the successfully trained model.
SegNet
DeepLab
and RefineNet were selected as comparison models. Experimental results showed that WWRSE accuracy improved by 4.2%
7.6%
and 8.6%
compared with the comparison models. Moreover
overall extraction accuracy reached 93%
thereby indicating that the method proposed in this study has certain advantages in proposing the spatial information distribution of winter wheat.
This method deeply explores the information contained in the class probability vector of the output of the full convolutional network and determines that the classification error is closely related to the small component difference in the class probability vector. Based on this finding
the classification result of the full convolution network is revised. The effectiveness and feasibility of the proposed method are proven by the experiments.
高分二号卷积神经网络RefineNet模型最大后验概率模型冬小麦空间分布章丘
GF-2full convolutional neural networksRefineNetmaximum aposteriori probabilitywinter wheatspatial distributionZhangqiu
Badrinarayanan V, Kendall A and Cipolla R. 2017. SegNet: a deep convolutional encoder-decoder architecture for imagesegmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495 [DOI: 10.1109/TPAMI.2016.2644615http://dx.doi.org/10.1109/TPAMI.2016.2644615]
Chen J, Chen T Q, Mei X M, Shao Q B and Deng M. 2014. Hilly farmland extraction from high resolution remote sensing imagery based on optimal scale selection. Transactions of the Chinese Society of Agricultural Engineering, 30(5): 99-107
陈杰, 陈铁桥, 梅小明, 邵权斌, 邓敏. 2014. 基于最优尺度选择的高分辨率遥感影像丘陵农田提取. 农业工程学报, 30(5): 99-107 [DOI: 10.3969/j.issn.1002-6819.2014.05.013http://dx.doi.org/10.3969/j.issn.1002-6819.2014.05.013]
Chen J J and Jin X G. 2015. Binary volume optimization based on maximum a posteriori-Markov random field. Journal of Computer-Aided Design and Computer Graphics, 27(7):1203-1210
陈俊杰, 金小刚. 2015. 基于最大后验概率-马尔科夫随机场的二进制体数据优化. 计算机辅助设计与图形学学报, 27(7):1203-1210 [DOI: 10.3969/j.issn.1003-9775.2015.07.008http://dx.doi.org/10.3969/j.issn.1003-9775.2015.07.008]
Chen L C, Papandreou G, Kokkinos I, Murphy K and Yuille A L. 2018a. DeepLab: semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834-848[DOI: 10.1109/TPAMI.2017.2699184http://dx.doi.org/10.1109/TPAMI.2017.2699184]
Fan J L and Lei B. 2009. Two-dimensional cross-entropy linear-type threshold segmentation method for gray-level images. Acta Electronica Sinica, 37(3): 476-480
范九伦, 雷博. 2009. 灰度图像的二维交叉熵直线型阈值分割法. 电子学报, 37(3): 476-480 [DOI:10.3321/j.issn:0372-2112.2009.03.009http://dx.doi.org/10.3321/j.issn:0372-2112.2009.03.009]
Feng M C, Yang W D, Zhang D Y, Cao L L, Wang H F and Wang Q. 2009. Monitoring planting area and growth situation of irrigation-land and dry-land winter wheat based on TM and MODIS data. Transactions of the CSAE, 25(3): 103-109
冯美臣, 杨武德, 张东彦, 曹亮亮, 王慧芳, 王芊. 2009. 基于TM和MODIS数据的水旱地冬小麦面积提取和长势监测. 农业工程学报, 25(3): 103-109
Fu G, Liu C J, Zhou R, Sun T and Zhang Q J. 2017. Classification for high resolution remote sensing imagery using a fully convolutional network. Remote Sensing, 9(6): 498[DOI: 10.3390/rs9050498http://dx.doi.org/10.3390/rs9050498]
Guo W Q, Ren J Q, Liu X R, Chen Z X, Wu S R and Pan H Z. 2018. Winter wheat mapping with globally optimized threshold under total quantiry constraint of statistical data. Journal of Remote Sensing, 22(6): 1023-1041
郭文茜, 任建强, 刘杏认, 陈仲新, 吴尚蓉, 潘海珠. 2018. 统计数据总量约束下全局优化阈值的冬小麦分布制图. 遥感学报, 22(6): 1023-1041 [DOI: 10.11834/jrs.20187468http://dx.doi.org/10.11834/jrs.20187468]
Hao W P, Mei X R,Cai X L, Du J T and Liu Q. 2011. Crop planting extraction based on multi-temporal remote sensing data in Northeast China. Transactions of the CSAE, 27(1): 201-207
郝卫平, 梅旭荣, 蔡学良, 杜建涛, 刘勤. 2011. 基于多时相遥感影像的东北三省作物分布信息提取. 农业工程学报, 27(1): 201-207 [DOI: 10.3969/j.issn.1002-6819.2011.01.033http://dx.doi.org/10.3969/j.issn.1002-6819.2011.01.033]
He H, Zhu X F, Pan Y Z, Zhu W Q, Zhang J S and Jia B. 2008. Study on scale issues in measurement of winter wheat plant area by remote sensing. Journal of Remote Sensing, 12(1): 168-175
何浩, 朱秀芳, 潘耀忠, 朱文泉, 张锦水, 贾斌. 2008. 尺度变化对冬小麦种植面积遥感测量区域精度影响的研究. 遥感学报, 12(1): 168-175 [DOI: 10.3321/j.issn:1007-4619.2008.01.022http://dx.doi.org/10.3321/j.issn:1007-4619.2008.01.022]
Hu F, Xia G S, Hu J W and Zhang L P. 2015. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery. Remote Sensing, 7(11): 14680-14707[DOI: 10.3390/rs71114680http://dx.doi.org/10.3390/rs71114680]
Huang J X, Luo Q,Liu X X and Zhang J. 2016. Winter wheat yield forecasting based on time series of MODIS NDVI. Transactions of the Chinese Society for Agricultural Machinery, 47(2): 295-301
黄健熙, 罗倩, 刘晓暄, 张洁. 2016. 基于时间序列MODIS NDVI的冬小麦产量预测方法. 农业机械学报, 47(2): 295-301 [DOI: 10.6041/j.issn.1000-1298.2016.02.039http://dx.doi.org/10.6041/j.issn.1000-1298.2016.02.039]
Li D R, Zhang L P and Xia G S. 2014. Automatic analysis and mining of remote sensing big data. Acta Geodaetica et Cartographica Sinica, 43(12): 1211-1216
李德仁, 张良培, 夏桂松. 2014. 遥感大数据自动分析与数据挖掘. 测绘学报, 43(12): 1211-1216[DOI: 10.13485/j.cnki.11-2089.2014.0187http://dx.doi.org/10.13485/j.cnki.11-2089.2014.0187]
Lin G S, Milan A, Shen C H and Reid I. 2016. RefineNet: multi-path refinement networks for high-resolution semantic segmentation.arXiv: 1611.06612
Lin H N, Shi Z W and Zou Z X. 2017. Maritime semantic labeling of optical remote sensing images with multi-scale fully convolutional network. Remote Sensing, 9(5): 480 [DOI:10.3390/rs9050480http://dx.doi.org/10.3390/rs9050480]
Liu C, Hong L, Chen J, Chu S S and Deng M. 2015. Fusion of pixel-based and multi-scale region-based features for the classification of high-resolution remote sensing image. Journal of Remote Sensing, 19(2): 228-239
刘纯, 洪亮, 陈杰, 楚森森, 邓敏. 2015. 融合像素—多尺度区域特征的高分辨率遥感影像分类算法. 遥感学报, 19(2): 228-239[DOI: 10.11834/jrs.20154035http://dx.doi.org/10.11834/jrs.20154035]
Liu D W, Han L and Han X Y. 2016. High spatial resolution remote sensing image classification based on deep learning. Acta Optica Sinica, 36(4): 298-306
刘大伟, 韩玲, 韩晓勇. 2016. 基于深度学习的高分辨率遥感影像分类研究. 光学学报, 36(4): 298-306 [DOI: 10.3788/AOS201636.0428001http://dx.doi.org/10.3788/AOS201636.0428001]
Mas J F and Flores J J. 2008. The application of artificial neural networks to the analysis of remotely sensed data. International Journal of Remote Sensing, 29(3):617-663 [DOI: 10.1080/01431160701352154http://dx.doi.org/10.1080/01431160701352154]
Meng X C, Shen H F, Zhang H Y, Zhang L P and Li H F. 2014. Maximum a posteriori fusion method based on gradient consistency constraint for multispectral/panchromatic remote sensing images. Spectroscopy and Spectral Analysis, 34(5):1332-1337
孟祥超, 沈焕锋, 张洪艳, 张良培, 李慧芳. 2014. 基于梯度一致性约束的多光谱/全色影像最大后验融合方法. 光谱学与光谱分析, 34(5): 1332-1337 [DOI: 10.3964/j.issn.1000-0593(2014)05-1332-06http://dx.doi.org/10.3964/j.issn.1000-0593(2014)05-1332-06]
Mountrakis G, Im J and Ogole C. 2011. Support vector machines in remote sensing: a review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3): 247-259[DOI: 10.1016/j.isprsjprs.2010.11.001http://dx.doi.org/10.1016/j.isprsjprs.2010.11.001]
Pringle M J, Denham R J and Devadas R. 2012. Identification of cropping activity in central and southern Queensland, Australia, with the aid of MODIS MOD13Q1 imagery. International Journal of Applied Earth Observation and Geoinformation, 19: 276-285[DOI: 10.1016/j.jag.2012.05.015http://dx.doi.org/10.1016/j.jag.2012.05.015]
Qian X L, Li J, Cheng G, Yao X W, Zhao S N, Chen Y B and Jiang L Y. 2018. Evaluation of the effect of feature extraction strategy on the performance of high-resolution remote sensing image scene classification. Journal of Remote Sensing, 22(5): 758-776
钱晓亮, 李佳, 程塨, 姚西文, 赵素娜, 陈宜滨, 姜利英. 2018. 特征提取策略对高分辨率遥感图像场景分类性能影响的评估. 遥感学报, 22(5): 758-776 [DOI: 10.11834/jrs.20188015http://dx.doi.org/10.11834/jrs.20188015]
Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention.Munich, Germany:Springer: 234-241 [DOI: 10.1007/978-3-319-24574-4_28http://dx.doi.org/10.1007/978-3-319-24574-4_28]
Shelhamer E, Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651 [DOI: 10.1109/TPAMI.2016.2572683http://dx.doi.org/10.1109/TPAMI.2016.2572683]
Sun Z R. 2015. Estimation of Winter Wheat Area and Drought Monitoring Research Based on Remote Sensing Data in Beijing-Tianjin-HebeiRegion. Beijing:Beijing Forestry University
孙振蓉.2015.京津冀地区冬小麦面积估算和旱情遥感监测研究. 北京: 北京林业大学
Visin F, Romero A, Cho K, Matteucci M, Ciccone M, Kastner K, Bengio Y and Courville A. 2016. ReSeg: a recurrent neural network-based model for semantic segmentation//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Las Vegas:IEEE: 426-433[DOI: 10.1109/CVPRW.2016.60http://dx.doi.org/10.1109/CVPRW.2016.60]
Wang J, Song J W, Chen M Q and Yang Z. 2015. Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine. International Journal of Remote Sensing, 36(12): 3144-3169 [DOI: 10.1080/01431161.2015.1054049http://dx.doi.org/10.1080/01431161.2015.1054049]
Wang L M, Liu J, Yao B M, Ji F H and Yang F G. 2018. Area change monitoring of winter wheat based on relationship analysis of GF-1 NDVI among different years. Transactions of the Chinese Society of Agricultural Engineering, 34(8): 184-191
王利民, 刘佳, 姚保民, 季富华, 杨福刚. 2018. 基于GF-1影像NDVI年度间相关分析的冬小麦面积变化监测. 农业工程学报, 34(8): 184-191 [DOI: 10.11975/j.issn.1002-6819.2018.08.024http://dx.doi.org/10.11975/j.issn.1002-6819.2018.08.024]
Wu C L, Chau K W and Fan C. 2010. Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. Journal of Hydrology, 389(1/2: 146-167 [DOI: 10.1016/j.jhydrol.2010.05.040http://dx.doi.org/10.1016/j.jhydrol.2010.05.040]
Wu M Q, Yang L C, Yu B, Wang Y, Zhao X, Niu Z and Wang C Y. 2014. Mapping crops acreages based on remote sensing and sampling investigation by multivariate probability proportional to size. Transactions of the Chinese Society of Agricultural Engineering, 30(2): 146-152
邬明权, 杨良闯, 于博, 王玉, 赵昕, 牛铮, 王长耀. 2014. 基于遥感与多变量概率抽样调查的作物种植面积测量. 农业工程学报, 30(2): 146-152 [DOI: 10.3969/j.issn.1002-6819.2014.02.019http://dx.doi.org/10.3969/j.issn.1002-6819.2014.02.019]
Xiao L, Wei Z H and Wu H Z. 2007. A generalized variational image restoration model based on map and robust estimation. Journal of Computer Research and Development, 44(7): 1105-1113
肖亮, 韦志辉, 吴慧中. 2007. 基于最大后验概率和鲁棒估计的图像恢复推广变分模型. 计算机研究与发展, 44(7): 1105-1113
Xu Q Y, Yang G J, Long H L, Wang C C, Li X C and Huang D C. 2014. Crop information identification based on MODIS NDVI time-series data. Transactions of the Chinese Society of Agricultural Engineering, 30(11): 134-144
许青云, 杨贵军, 龙慧灵, 王崇倡, 李鑫川, 黄登成. 2014. 基于MODISNDVI多年时序数据的农作物种植识别. 农业工程学报, 30(11): 134-144 [DOI: 10.3969/j.issn.1002-6819.2014.11.017http://dx.doi.org/10.3969/j.issn.1002-6819.2014.11.017]
You J, Pei Z Y, Wang F, Wu Q and Guo L. 2016. Area extraction of winter wheat at county scale based on modified multivariate texture and GF-1 satellite images. Transactions of the Chinese Society of Agricultural Engineering, 32(13): 131-139
游炯, 裴志远, 王飞, 吴全, 郭琳. 2016. 基于改进多元纹理信息模型和GF-1影像的县域冬小麦面积提取. 农业工程学报, 32(13): 131-139 [DOI: 10.11975/j.issn.1002-6819.2016.13.019http://dx.doi.org/10.11975/j.issn.1002-6819.2016.13.019]
Zhang C M, Gao S, Yang X X, Li F, Yue M R, Han Y J, Zhao H, Zhang Y N and Fan K Q. 2018a. Convolutional neural network-based remote sensing images segmentation method for extracting winter wheat spatial distribution. Applied Sciences, 8(10): 1981 [DOI: 10.3390/app8101981http://dx.doi.org/10.3390/app8101981]
Zhang C M, Liu J P, Yu F, Wan S J, Han Y J, Wang J and Wang G. 2018b. Segmentation model based on convolutional neural networks for extracting vegetation from Gaofen-2 images. Journal of Applied Remote Sensing, 12(4): 042804 [DOI: 10.1117/1.JRS.12.042804http://dx.doi.org/10.1117/1.JRS.12.042804]
Zhang J H, Feng L L and Yao F M. 2014. Improved maize cultivated area estimation over a large scale combining MODIS–EVI time series data and crop phenological information. ISPRS Journal of Photogrammetry and Remote Sensing, 94: 102-113 [DOI: 10.1016/j.isprsjprs.2014.04.023http://dx.doi.org/10.1016/j.isprsjprs.2014.04.023]
Zhao L J and Tang P. 2016. Scalability analysis of typical remote sensing data classification methods: a case of remote sensing image scene. Journal of Remote Sensing, 20(2): 157-171
赵理君, 唐娉. 2016. 典型遥感数据分类方法的适用性分析-以遥感图像场景分类为例. 遥感学报, 20(2): 157-171 [DOI: 10.11834/jrs.20164279http://dx.doi.org/10.11834/jrs.20164279]
相关作者
相关机构
京公网安备11010802024621