Research On Change Detection Of Remotely Sensed Imagery And GIS

Change Detection in remote sensing imagery is defined as the procedure of quantitatively analyzing and identifying changes occurred on the earth's surface from remote sensing imageries acquired at different times. By analyzing multi-temporal remote sensing images about same region, change detection is used to provide land change information that is of great significance, has been applied widely.This paper fisrtly points out the important meaning of change detection in remote sensing imagery to the science research and industry production based on the background of problem studied, and analyzes the current status and developing trend of the change detection. And then the basic principles, features and problems of change detection are summarized. The change detection in remote sensing imagery is researched thoroughly.Three algorithms are put forward in this thesis for change detection in remote sensing imagery, a new method named a solution using proliferation of area to determine the threshold is proposed.A threshold has been taken from typical area based on change vector analysis and carry on the the whole image.The results show that this method improve the change detection precision and the advantages of this method significantly. A new independent component analysis (ICA) change detection based on the wavelet transform is proposed.Through analyzing the character of wavelet transform, the block data is optimized. The experimental results demonstrate that algorithm enough considerate all independence and the contextual information. A method is presented to change detection based on the line change detection and difference image. Enough consider the line feature of the line object and the edge and gray information to detect the changes,the results improve that the method is so good. Experiental results demonstrate that the algorithm proprosed in this paper is effective for indentifying and extracting changed areas from liner detection.