浏览全部资源
扫码关注微信
Published： 2017-5 ，
Accepted： 20 February 2017
扫 描 看 全 文
王娜, 李强子, 杜鑫, 张源, 赵龙才, 王红岩. 2017. 单变量特征选择的苏北地区主要农作物遥感识别. 遥感学报, 21(4): 519–530
Wang N, Li Q Z, Du X, Zhang Y, Zhao L C and Wang H Y. 2017. Identification of main crops based on the univariate feature selection in Subei. Journal of Remote Sensing, 21(4): 519–530
遥感识别多源特征综合和特征优选是提高遥感影像分类精度的关键技术。农作物遥感识别中，识别特征的相对单一和数量过多均会导致作物识别精度不理想。随机森林(random forests)采用分类与回归树(CART)算法来生成分类树，结合了bagging和随机选择特征变量的优点，是一种有效的分类方法。单变量特征选择(univariate feature selection)能够对每一个待分类的特征进行测试，衡量该特征和响应变量之间的关系，根据得分舍弃不好的特征，优选得到的特征用于分类。本文基于随机森林和单变量特征选择，利用多时相光谱信息、植被指数信息、纹理信息及波段差值信息，设计多组分类实验方案，对江苏省泗洪县的高分一号(GF-1)和环境一号(HJ-1A)影像进行分类研究，旨在选择最佳的分类方案对实验区主要农作物进行识别和提取。实验结果表明：(1)多源信息综合的农作物分类精度明显高于单一的原始光谱特征分类，说明不同类型特征的引入能改善分类效果；(2)基于单变量特征选择算法的优选特征分类效果最佳
总体精度97.07%，Kappa系数0.96，表明了特征优选在降低维度的同时，也保证了较高的分类精度。随机森林和单变量特征选择结合的方法可以提高遥感影像的分类精度，为农作物的识别和提取研究提供了有效的方法。
Timely accurate crop type identification and Crop Acreage Estimates (CAE) are essential for food security. Remote sensing technology has been successfully applied to crop identification because of its macro
rapid monitoring capabilities at large scales and its ability to quickly obtain accurate agricultural information. However
when identifying crop types
both simple and too many identifiable features might lead to low classification accuracies. Thus
multi-source and optimally selected features are obviously crucial to crop classification using remotely-sensed images. This paper considered a series of features
including multi-temporal spectra
vegetation indexes
textures
and band differences. Multiple experiments were designed and conducted in Sihong County
Jiangsu Province
China using Gaofen-1 and Huanjing-1 images to evaluate the influence of different features on the identification accuracy and determine the combination of preferred features which can improve the classification effect. The combination of random forest classification and univariate feature selection methods was expected to have a considerably positive effect on distinguishing and extracting the main crops in remote sensing images. In this study
the crop classification was implemented using random forests and univariate feature selection. The random forest method
which constructs many CART decision trees during each classification process
is one of themost effective classification methods. Univariate feature selection is a statistical testing method
which tests each feature to measure the relationship between the feature and the corresponding variable and then removes features that obtain low scores. First
the random forest classifier was applied to classify the images using the preceding multisource features mentioned. Second
we analyzed the contributions of different types of features or feature combinations to the classification accuracy. Third
features were selected by using the univariate feature selection method. Finally
we re-combined the optimal features and random forest to classify the image and distinguish the main crop types with high accuracy. The results showed that overall classification accuracy based on the combination of optimal features reached 97.07% with the corresponding Kappa coefficient being 0.96
which indicated that the feature selection method used in this paper has a considerably positive effect on high classification accuracy because it efficiently reduced feature dimension. The classification results also showed that the crop classification using multi-source features outperformed the one which only used spectral features. In addition
the accuracy of the experiment which simultaneously used spectral and VI features was the second highest among all experiments. The optimal feature combination has 19 features
including five spectral features
six vegetation indexes
seven band difference features
and 1 texture feature
which suggested that vegetation indexes and band differences were more important to the crop identification than the other two. This study demonstrated the following: (1) the addition of different types of features could improve classification accuracy; (2) too many features would decrease classification accuracies; (3) univariate feature selection was effective for choosing the optimal subset of features. The optimally selected features can be relatively beneficial to reduce the computation load and improve the worse accuracies caused by applied features blindly. Therefore
the combination of random forest and univariate feature selection is effective in improving classification accuracy and efficiency.
单变量特征选择光谱特征植被指数特征纹理特征波段差值特征
univariate feature selectionspectrum featureVegetation Index (VI) featuretexture featureband difference features
Atkinson J T, Ismail R and Robertson M. 2014. Mapping bugweed (solanum mauritianum) infestations in pinus patula plantations using hyperspectral imagery and support vector machines. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(1): 17–28
Blum A L and Langley P. 1997. Selection of relevant features and examples in machine learning. Artificial Intelligence, 97(1/2): 245–271
Breiman L. 2001. Random forest. Machine Learning, 45(1): 5–32
Chakraborty M and Panigrahy S. 2000. A processing and software system for rice crop inventory using multi-date RADARSAT ScanSAR data. Isprs Journal of Photogrammetry and Remote Sensing, 55(2): 119–128
陈启浩. 2007. 面向对象的多源遥感数据分类技术研究与实现. 武汉: 中国地质大学: 17–18
Chen Q H. 2007. Researeh and realization of multi-source remote sensing data on objeet oriente. Wuhan: China University of Geosciences: 17–18
程希萌, 沈占锋, 邢廷炎, 夏列钢, 吴田. 2016. 基于mRMR特征优选算法的多光谱遥感影像分类效率精度分析. 地球信息科学学报, 18(6): 816–823
Chen X M, Shen Z F, Xing T Y, Xia L G and Wu T J. 2016. Efficiency and accuracy analysis of multispectral image classification based on mRMR feature selection method. Journal of Geo-information Science, 18(6): 816–823
丁娅萍. 2013. 基于微波遥感的旱地作物识别及面积提取方法研究. 北京: 中国农业科学院: 4–42
Ding Y P. 2013. Research on dryland crops identification and area extraction method based on microwave remote sensing. Beijing: Chinese Academy of Agricultural Sciences: 4–42
Drotár P, Gazda J and Smékal Z. 2015. An experimental comparison of feature selection methods on two-class biomedical datasets. Computers in Biology and Medicine, 66: 1–10
Jarvis E. 2016. 结合Scikit-learn介绍几种常用的特征选择方法[EB/OL]. 2016-06-27.http://dataunion.org/ 14072.htmlhttp://dataunion.org/14072.html
Jarvis E. 2016. The introduction of some common feature selction methods with scikit-learn[EB/OL]. 2016-06-27.http://dataunion. org/14072.htmlhttp://dataunion.org/14072.html
Jia K, Li Q Z, Tian Y C, Wu B F, Zhang F F and Meng J H. 2012. Crop classification using multi-configuration SAR data in the North China Plain. International Journal of Remote Sensing, 33(1): 170–183
贾坤, 李强子. 2013. 农作物遥感分类特征变量选择研究现状与展望. 资源科学, 35(12): 2507–2516
Jia K and Li Q Z. 2013. Review of features selection in crop classification using remote sensing data. Resources Science, 35(12): 2507–2516
Kaya G T. 2013. A comprehensive analysis of earthquake damage patterns using high dimensional model representation feature selection//Proc. SPIE 8892, Image and Signal Prcessing for Remote Sensing XIX. Dresden, Germany: SPIE [DOI: 10.1117/12. 2030100]
雷震. 2012. 随机森林及其在遥感影像处理中应用研究. 上海: 上海交通大学: 9–12
Lei Z. 2012. Random Forest and its application in remote sensing. Shanghai: Shanghai Jiaotong University: 9–12
Liu H and Yu L. 2005. Toward integrating feature selection algorithms for classification and clustering. IEEE Transactions on Knowledge and Data Engineering, 17(4): 491–502
刘扬, 付征叶, 郑逢斌. 2015. 高分辨率遥感影像目标分类与识别研究进展. 地球信息科学学报, 17(9): 1080–1091
Liu Y, Fu Z Y and Zheng F B. 2015. Review on high resolution remote sensing image classification and recognition. Journal of Geo-information Science, 17(9): 1080–1091
Lu D and Weng Q. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5): 823–870
马玥, 姜琦刚, 孟治国, 李远华, 王栋, 刘骅欣. 2016. 基于随机森林算法的农耕区土地利用分类研究. 农业机械学报, 47(1): 297–303
Ma Y, Jiang Q G, Meng Z G, Li Y H, Wang D and Liu H X. 2016. Classification of land use in farming area based on Random Forest algorithm. Transactions of The Chinese Society of Agricultural Machinery, 47(1): 297–303
Persello C and Bruzzone L. 2009. A novel approach to the Selection of spatially invariant features for classification of hyperspectral images//2009 IEEE International Geoscience and Remote Sensing Symposium. Cape Town: IEEE: II-61-II-64 [DOI: 10.1109/ igarss.2009.5418001]
任建强, 陈仲新, 唐华俊, 周清波, 秦军. 2011. 基于遥感信息与作物生长模型的区域作物单产模拟. 农业工程学报, 27(8): 257–264
Ren J Q, Chen Z X, Tang H J, Zhou Q B and Qin J. 2011. Regional crop yield simulation based on crop growth model and remote sensing data. Transactions of the CSAE, 27(8): 257–264
Soares J V, Rennó C D, Formaggio A R, da Costa Freitas Yanasse C and Frery A C. 1997. An investigation of the selection of texture features for crop discrimination using SAR imagery. Remote Sensing of Environment, 59(2): 234–247
Tuia D, Pacifici F, Kanevski M and Emery W J. 2009. Classification of very high spatial resolution imagery using mathematical morphology and support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 47(11): 3866–3879
Wang D, Lin H, Chen J S, Zhang Y Z and Zeng Q W. 2010. Application of multi-temporal ENVISAT ASAR data to agricultural area mapping in the Pearl River Delta. International Journal of Remote Sensing, 31(6): 1555–1572
王书玉, 张羽威, 于振华. 2014. 基于随机森林的洪河湿地遥感影像分类研究. 测绘与空间地理信息, 37(4): 83–93
Wang S Y, Zhang Z W and Yu Z H. 2014. Classification of Honghe Wetland remote sensing image based on random forests. Geomatics and Spatial Information Technology, 37(4): 83–93
吴炳方. 2004. 中国农情遥感速报系统. 遥感学报, 8(6): 481–497
Wu B F. 2004. China crop watch system with remote sensing. Joural of Remote Sensing, 8(6): 481–497
Yang C, Liu S C, Bruzzone L, Guan R C and Du P J. 2013. A feature-metric-based affinity propagation technique for feature selection in hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 10(5): 1152–1156
杨珺雯, 张锦水, 朱秀芳, 谢登峰, 袁周米琪. 2015. 随机森林在高光谱遥感数据中降维与分类的应用. 北京师范大学学报(自然科学版), 51(S1): 82–88
Yang J W, Zhang J S, Zhu X F, Xie D F and Yuan Z M Q. 2015. Random Forest applied for dimension reduction and classification in hyperspectral data. Journal of Beijing Normal University (Natural Science), 51(S1): 82–88
姚登举, 杨静, 詹晓娟. 2014. 基于随机森林的特征选择算法. 吉林大学学报(工学版), 44(1): 137–141
Yao G J, Yang and Zhan X J. 2014. Feature selection agorithm based on random forest. Journal of Jilin University (Engineering and Technology Edition), 44(1): 137–141
Zortea M and Haertel V. 2004. Experiments on feature extraction in remotely sensed hyperspectral image data//IEEE International Geoscience and Remote Sensing Symposium. [s.l.]: IEEE: 964–967[DOI: 10.1109/igarss.2004.1368569]
相关文章
相关作者
相关机构
京公网安备11010802024621