结合RBF网络与光谱指数的遥感分类应用研究
Application Study on Remote Sensing Classification Based on RBF Network and Spectral Indexes
DOI: 10.12677/HJWC.2014.46021, PDF, HTML, 下载: 2,400  浏览: 9,874  国家科技经费支持
作者: 黄三军, 郝莹莹：重庆邮电大学计算机学院，重庆；罗小波：西南大学资源环境学院，重庆
关键词: RBF神经网络；光谱指数；城市土地利用；分类；RBF Neural Network； Spectral Index； Urban Land Use； Classification
摘要: 本文基于光谱波段信息，提取NDWI、NDVI、NDBI三种归一化指数，作为城市地区土地利用分类的关键辅助信息。在此基础上，提出基于RBF网络与归一化指数的城市遥感分类模型。最后，以四川南充市为研究区域，以TM影像为数据源，对本文提出的城市地区分类模型进行了分类实验。实验结果表明，RBF在融合地学参数方面具有一定的优势，基于RBF神经网络与地表指数进行分类，能获得95.02%的较为理想的总体分类精度，比单纯利用波段信息进行分类其精度提高了7.05个百分点。
Abstract: In this paper, spectral indexes NDWI, NDVI, NDBI were inversed from TM images as the key aux-iliary information in the classification of city land use. On this basis, the city remote sensing classi-fication model was put forward based on RBF network and the normalized indexes. Finally, taking the Sichuan Nanchong city as the study area, using TM image as data source, the city classification model proposed in this paper was experimented. The experimental results show that RBF network has a certain advantage in the integration of learning parameters. The overall accuracy using RBF neural network and the surface indexes can reach to 95.02%, which is improved by 7.05 percentage points than only using the band information.
文章引用：黄三军, 郝莹莹, 罗小波. 结合RBF网络与光谱指数的遥感分类应用研究[J]. 无线通信, 2014, 4(6): 136-142. http://dx.doi.org/10.12677/HJWC.2014.46021

参考文献

[1] Pasolli, E., Farid, M. and Tuia, D. (2014) SVM active learning approach for image classification using spatial information. IEEE Transactions on Geoscience and Remote Sensing, 52, 2217-2223.
[2] Zhang, R., Sun, D.L. and Li, S.M. (2013) A stepwise cloud shadow detection approach combining geometry determination and SVM classification for MODIS data. International Journal of Remote Sensing, 34, 211-226.
[3] Andreas, B., Uwe, W. and Stefan, H. (2012) Classification in high dimensional feature spaces assessment using SVM, IVM and RVM with focus on simulated EnMAP data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5, 436-443.
[4] Du, P.J., Tan, K. and Xing, X.S. (2010) Wavelet SVM in Reproducing Kernel Hilbert Space for hyper spectral remote sensing image classification. Optics Communications, 283, 4978-4984.
[5] Chen, S.J., Hu, Y.H. and Sun, D.J. (2014) Classification of hyper spectral remote sensing image based on nonlinear kernel mapping and artificial immune network. Journal of Infrared and Millimeter Waves, 33, 289-296.
[6] Xu, J.B., Song, L.S. and Zhong, D.F. (2013) Remote sensing image classification based on a modified self-organizing neural network with a priori knowledge. Sensors and Transducers, 153, 29-36.
[7] Han, M., Zhu, X.R. and Yao, W. (2012) Remote sensing image classification based on neural network ensemble algorithm. Neurocomputing, 78, 133-138.
[8] Luo, K., Luo, X. and Feng, Z.K. (2008) Application of SOFM neural network in classification of remote sensing images. Journal of Beijing Forestry University, 30, 73-77.
[9] Solares, C. and Sanz, A.M. (2005) Bayesian network classifiers. An application to remote sensing image classification. WSEAS Transactions on Systems, 4, 343-348.
[10] Tan, K. and Du, P.-J. (2013) Hyperspectral remote sensing image classification based on radical basis function neural network. Spectroscopy and Spectral Analysis, 28, 2009-2013.
[11] Luo, J.C., Ming, D.P. and Shen, Z.F. (2005) Elliptical basis function network for classification of remote-sensing images. Journal of Data Acquisition and Processing, 20, 8-12.
[12] Bruzzone, L. and Prieto, D.F. (1999) Technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing, 37, 1179-1184.
[13] Foody, G.M. (2004) Supervised image classification by MLP and RBF neural networks with and without an exhaustively defined set of classes. International Journal of Remote Sensing, 2, 3091-3104.
[14] Su, W., Li, J. and Chen, Y.H. (2008) Textural and local spatial statistics for the object-oriented classification of urban areas using high resolution imagery. International Journal of Remote Sensing, 29, 3105-3117.
[15] Aguilar, M.A., Saldaña, M.M. and Aguilar, F.J. (2013) GeoEye-1 and WorldView-2 pan-sharpened imagery for object-based classification in urban environments. International Journal of Remote Sensing, 34, 2583-2606.
[16] De Pinho, C.M.D. and Fonseca L.M.G. (2012) Land-cover classification of an intra-urban environment using high- resolution images and object-based image analysis. International Journal of Remote Sensing, 33, 5973-5995.
[17] 吴田军, 骆剑承, 夏列钢 (2014) 等迁移学习支持下的遥感影像对象级分类样本自动选择方法. 测绘学报, 43, 908-916.
[18] 夏列钢, 骆剑承, 王卫红 (2014) 遥感信息图谱支持的土地覆盖自动分类. 遥感学报, 18, 796-893.
[19] 刘培, 杜培军, 谭琨 (2014) 一种基于集成学习和特征融合的遥感影像分类新方法. 红外与毫米波, 33, 311-317.
[20] Luo, X.B., Liu, Q.H. and Liu, Q. (2012) Research on remote sensing classification based on improved Kohonen neural network. 2nd International Conference on Computer Engineering and Technology, 4, 545-547.
[21] Luo, X.B. and Li, W.S. (2014) Scale effect analysis of the relationships between urban heat island and impact factors: Case study in Chongqing. Journal of Applied Remote Sensing, 8, 084995.