Abstract: Through analyzing problems brought on change detection methods of remote sensing images with high resolution,a novel change detection algorithm using Independent Component Analysis combined with oriented-object and undecimated discrete wavelet transform (UDWT) was proposed．First,feature images of image’s objects extracted using oriented-object method serve as data of input vector to estimate sub-space for Independent Component Analysis,which can improve effect of noise suppression,simultaneously,a new algorithm using self-adapted weight was proposed in order to extract image’s object,which optimizes processing method on oriented-object deeply.New partitioning scheme using undecimated discrete wavelet transform overcomes effectively prominent problem as follows:the size of input vector becomes shrinking which leads to unprecisely estimation of sub-space for independent component analysis using present partitioning scheme． Simulation results show that compared with typical algorithm,such as Independent Component Analysis and undecimated discrete wavelet transform, new algorithm improves robust and veracity of change detection for high-resolution images greatly by using qualitative and quantitative results.

Key words: Image’s objects,Change detection,UDWT,ICA