基于獨立成分分析的多時相遙感圖像變化檢測
Multitemporal Remote Sensing Images Change Detection Based on ICA
-
摘要: 變化檢測是通過分析多時相遙感圖像間的差異實現(xiàn)地物變化信息的提取，而消除多時相遙感圖像中的相關(guān)性是提取變化信息的一種有效途徑。獨立成分分析(ICA)作為近年出現(xiàn)的盲源分離技術(shù)，能夠有效地消除多源信號間的二階和高階相關(guān)，經(jīng)其變換的各分量之間相互獨立。該文提出一種應(yīng)用ICA變換實現(xiàn)多時相遙感圖像變化檢測的算法，首先對多時相多光譜遙感圖像進行獨立成分分析，得到彼此沒有相關(guān)信息的獨立成分，并且各獨立成分圖像中的變化信息得到增強；然后通過分析變換后的獨立成分實現(xiàn)地物的變化檢測。實驗結(jié)果顯示該算法比傳統(tǒng)的方法具有更好的性能。
-
關(guān)鍵詞:
- 遙感變化檢測;圖像處理;獨立成分分析;多時相圖像;主成分分析
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 -
計量
- 文章訪問數(shù): 3379
- HTML全文瀏覽量: 104
- PDF下載量: 2358
- 被引次數(shù): 0
下載:
