全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

行程长度纹理特征在SPOT遥感图像分类中的应用

, PP. 260-265

Keywords: 遥感图像分类,行程长度纹理特征,Rough集,神经网络

Full-Text   Cite this paper   Add to My Lib

Abstract:

将行程长度纹理特征与神经网络相结合应用于遥感图像分类中.在特征选择阶段采用类内、类间方差标准与Rough集相结合的方法挑选出有较强分类能力的特征并有效去除冗余特征.针对高分辨率、大尺度的SPOT全色遥感卫星图像,分别基于行程长度纹理特征、共生矩阵纹理特征、灰度梯度共生矩阵纹理特征和灰度平滑共生矩阵纹理特征,采用BP、RBF两种类型的神经网络以及最近邻分类算法(KNN法)对其进行分类,并对分类结果进行对比.实验结果证明本文算法的有效性.

References

[1]  Zhou Chenghu, Luo Jiancheng. Remote Sensing Comprehension and Analysis. Beijing, China: Science Press, 2003 (in Chinese) (周成虎,骆剑承.遥感影像地学理解与分析.北京:科学出版社, 2003)
[2]  Tang Xiaoou. Texture Information in RunLength Matrices. IEEE Trans on Image Processing, 1998, 7(11): 16021609
[3]  Galloway M M. Texture Analysis Using Gray Level Lengths. Computer Graphics and Image Processing, 1975, 1(4): 172179
[4]  Chu A, Sehgal C M, Greenleaf J F. Use of Gray Value Distribution of Run Lengths for Texture Analysis. Pattern Recognition Letters, 1990, 11(6): 415420
[5]  Dasarathy B R, Holder E B. Image Characterizations Based on Joint GrayLevel RunLength Distributions. Pattern Recognition Letters, 1991, 12(8): 497502
[6]  Pawlak Z. Rough Sets. International Journal of Information and Computer Science, 1982, 11(5): 145172
[7]  Sun Lixin, Gao Wen. Method of Selecting the Best Classification Bands from Hyperspectral Images Based on Genetic Algorithm and Rough Set. Proc of SPIE, 1998, 3502: 179184
[8]  Atkinson P M, Tatnall A R L. Neural Network in Remote Sensing. Remote Sensing, 1997, 18(4): 699709
[9]  Yu Chunyan, Wu Minghui, Wu Ming. Combining Rough Set Theory with Neural Network for Remote Sensing Image. Journal of Remote Sensing, 2004, 8(4): 331338 (in Chinese) (余春艳,吴明辉,吴 明.遥感图像识别中粗糙集理论与神经网络的结合.遥感学报, 2004, 8(4): 331338)
[10]  Wu Zhaocong. RBFNN Representation Based on Rough Sets and Its Application to Remote Sensing Classification. Acta Geodaetica et Cartographica Sinica, 2003, 32(1): 5357 (in Chinese) (巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用.测绘学报, 2003, 32(1): 5357)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133