Abstract:When percentage of changed area in whole scene is relatively too small or too large, general change detection methods can not detect the change information accurately. In order to solve this problem, this paper proposes a split window-based method for unsupervised change detection in multichannel remotely sensed images. This method splits difference image into a set of subimages, and determines segmentation threshold of the whole scene by combining the thresholds of subimages. Experimental results demonstrate that the proposed method can detect change information accurately even if percentage of changed area in whole scene is relatively too small or too large, and improve detection accuracy obviously comparing to general change detection methods.