Gaussian process（GP） represents a powerful theoretical framework for Bayesian classification.Despite GP classifier have gained prominence in recent years

it remains an approach whose potentialities are not yet sufficiently known in remote sensing community.This paper gives a thorough investigation of GP CLASSIFIER for high resolution（HR） multi-temporal image change detection.Firstly

we give a detailed analysis of the capabilities of GP classifier in theory.Secondly

we elaborately explore the advantages and disadvantages of the GP classifiers.Finally

we design several experiments to test the performance of the GP classifier for HR remote sensing image change detection.Moreover

we propose a novel approach for improving the capacities of GP classifier in remote sensing image change detection.The proposed context-sensitive change detection method is achieved by analyzing the posterior probability of probabilistic GP classifier within a markov random field（MRF） framework.In particular

the method consists of two steps:（1） A supervised initialization is founded on a probabilistic GP classifier;（2） A MRF regularization aims at refining the posterior probability by employing the spatial context information.Five experiments carried out on HR remote sensing image set validate the power of GP classifier for change detection and also the effectiveness of our proposed methods.