Abstract: A kernel change detection algorithm(KCD) is proposed.The input vectors from two images of different times are mapped into feature space of high dimension via a nonlinear mapping.Which will usually increase the linear separation of change and no-change regions.Then,a simple linear distance measure between two feature vectors of high dimension is defined in features space,which corresponds to the complicated nonlinear distance measure in input space.Furthermore,the distance measure's dot is expressed in the combination of kernel functions and large numbers of dot operations processed in input space not in feature place by combined kernel tactic,which avoids the operation burden in high dimension space.The soft margin single-class support vector machine(SVM) is taken to select the optimal hyper-plane.Results show that KCD has excellent performance in speed and accuracy.