用于Landsat ETM+和ERS-2 SAR图像融合对城区地物特征分类的BP-ANN/GA混合算法
A Hybrid BP-ANN/GA Algorithm for Classification of Urban Terrain Surfaces Using Fused Images of Landsat ETM+ and ERS-2 SAR
-
摘要: 该文建立了反向传播人工神经网络 (Back Propagation Artificial Neural Network, BP-ANN)和遗传算法 (Genetic Algorithm, GA)的BP-ANN/GA混合算法。利用GA算法的全局优化能力优化BP-ANN的初始权值，克服了传统BP-ANN收敛速度慢，容易陷入局部最小的缺点。BP-ANN/GA混合算法对Landsat ETM+4, 5, 7三波段红外图像和ERS-2 SAR雷达图像的融合数据进行了城市多类地物特征分类。结果表明：BP-ANN/GA算法不仅提高多源遥感图像自动分类的速度，而且提高了各类特征分类的精度。该文对上海浦东地区的Landsat ETM＋和ERS-2 SAR数据作了融合分类试验与验证。
-
关键词:
- 图像融合;BP-ANN/GA;地表分类
Abstract: A hybrid algorithm of the BP-ANN/GA (Back Propagation Artificial Neural Network and Genetic Algorithm) is developed to optimize the initial weights and make fast convergence of the BP-ANN. This algorithm is applied to classification of urban terrain surfaces with fused data of Landsat ETM+ and ERS-2 SAR. An example of the Shanghai Pudong area using both the Landsat ETM+ and ERS-2 SAR image data well demonstrates the classification speed and accuracy of the algorithm. -
边肇祺. 模式识别 (第二版)[M]. 北京：清华大学出版社，2000.01: 46.159.[2]Yoshida T, Omatu S. Neural network approach to land cover mapping [J]. IEEE Trans. on Geosci. Remote Sens. 1994, 32(5):11031109. .合肥：中国科学技术大学出版社, 2003.05: 5587. .[3]Hansen J V, McDonald J B. Some experimental evidence on the performance of GA-designed neural networks [J].Journal of Experimental Theoretical Artificial Intelligence.2001, 13(3):-[4]周明, 孙树栋. 遗传算法原理及应用(第一版) [M]. 北京：国.64. 防工业出版社, 1999.06: 1[5]Jin Y Q, Wang Y. A genetic algorithm to retrieve multi- parameters of land surface roughness and soil moisture [J]. International Journal of Remote Sensing, 2001, 22(16): 3093307321. .[6]李祚泳. 用B-P神经网络实现多波段遥感图像的监督分类[J]. 红外与毫米波学报, 1998, 17(2): 153156. 3099...[7]Lopbs A, Nezry E, Touzi R, Laur H. Structure detection and statistical adaptive speckle filtering in SAR images [J]. International Journal of Remote Sensing, 1993, 14(9): 17351758.[8]Gonzalez R C, Woods R E. Digital image processing (second edition) [M], New York: Prentice-Hall, 2003: 675.683. -
计量
- 文章访问数: 2569
- HTML全文浏览量: 118
- PDF下载量: 986
- 被引次数: 0
下载:
