Automatic Change Detection Based on Codelength Differences in Multi-temporal and Multi-spectral Images

摘要

We propose a technique for detecting significant changes in a scene automatically, based on images acquired at different times. Compared to conventional luminance difference methods, the proposed technique does not require an arbitrarily-determined threshold for deciding how much change in pixel values amounts to a significant change in the scene. The technique can be used to detect the changes that occured in the scene, even when the images are of different spectral domains.