Improving change detection accuracy by exploiting multispectral information

In this paper an algorithm to detect changes in multispectral and multitemporal remote-sensing images is presented. Such an algorithm makes it possible to reduce the effects of "registration noise" on the accuracy of change detection. In addition, it can be used to reduce the number of typologies of detected changes in order to better point out the changes under investigation. ©2005 Copyright SPIE - The International Society for Optical Engineering