The problem how to combine the low precision urban land use cover classifiers to get higher precision is dealt with in this paper. Using 2007 Shanghai CBERS (China-Brazil Earth Resources Satellite) images, the authors adopted the AdaBoost combination classifier, which can combine spectral feature information, texture structure information and decision tree classier to improve the classification precision. The experiment results show that a notable improvement of the classification precision of urban land use cover can be achieved by using AdaBoost algorithm.