基于独立成分分析的多时相遥感图像变化检测
Multitemporal Remote Sensing Images Change Detection Based on ICA
-
摘要: 变化检测是通过分析多时相遥感图像间的差异实现地物变化信息的提取，而消除多时相遥感图像中的相关性是提取变化信息的一种有效途径。独立成分分析(ICA)作为近年出现的盲源分离技术，能够有效地消除多源信号间的二阶和高阶相关，经其变换的各分量之间相互独立。该文提出一种应用ICA变换实现多时相遥感图像变化检测的算法，首先对多时相多光谱遥感图像进行独立成分分析，得到彼此没有相关信息的独立成分，并且各独立成分图像中的变化信息得到增强；然后通过分析变换后的独立成分实现地物的变化检测。实验结果显示该算法比传统的方法具有更好的性能。Abstract: Change detection is the process of identifying differences in the state of an object or phenomenon by observing it at different times. by removing the correlation among multitemporal images, change information can be detected effectively. Independence Component Analysis (ICA) is a blind source separate technique appeared in recent years. It can reduce second and high-order dependences in observed data, and the independent components are statistically as independent as possible. In this paper, a multitemporal remote sensing images change detection approach based on ICA is proposed in this paper. Firstly, independence component images change are obtained based on the ICA transformation without any prior knowledge about change areas. Then, different kinds of land variation are located according to these independent source images. The experimental results in synthesize and real multitemporal images show the effectiveness of the proposed approach.
-
Singh A. Digital change detection techniques using remotely sensed data [J].Int. J. Remote Sensing.1989, 10 (6):989-1003[2]Jensen J R. Introductory Digital Image Processing: A Remote Sensing Perspective [M]. New Jersey, Prentice Hall, 1996.[3]Bruzzone L, Prieto D F. Automatic analysis of the difference image for unsupervised change detection [J].IEEE Trans. on Geosci. Remote Sensing.2000, 38 (3):1171-1182[4]Hyv鋜inen A, Karhunen J, Oja E. Independent Component Analysis [M], New York: Wiley, 2001.[5]Fran J, Cardoso C. Blind signal separation: statistical principles [J].Proc. IEEE.1998, 86 (10):2009-2025[6]Chang C I, Chiang S S, J. Smith A, Ginsberg I WLinear spectral random mixture analysis for hyperspectral imagery [J].. IEEE Trans.on Geosci. Remote Sensing.2002, 40 (2):375-392[7]Jenssen R, Eltoft T. Independent component analysis for texture segmentation [J].Pattern Recognition.2003, 36:2301-2315[8]Hyvarinen A. Fast and robust fixed point algorithms for independent component analysis [J].IEEE Trans. on Neural Network.1999, 10 (3):626-634[9]Amari S. Natural gradient works efficiently in learning [J].Neural Computation.1998, 10:251-276 -
计量
- 文章访问数: 3356
- HTML全文浏览量: 103
- PDF下载量: 2358
- 被引次数: 0
下载:
