Abstract: Objective The assumption that the spectral responses of different types of objects in different periodshave the same linear relationship in traditional relative radiometric normalization is insufficient for theanalysis of high resolution remote sensing images.Object-oriented relative radiometric normalizationfor high resolution remote sensing image change detection is proposed in the paper based on the as-sumption that the spectral responses of different types of objects in different periods have different lin-ear relationships.Firstly,image objects are divided into two categories:changed and unchanged bycorrelation coefficients.Secondly,gains and offset parameters are calculated by an analysis of a ran-dom sampling consensus based on unchanged image objects.Thirdly,gains and offset parameters ofthe unchanged image objects which are most similar with the changed image objects are assigned to thechanged image objects.Lastly,the image objects are corrected using gain and offset parameters.Ex-periments on high resolution remote sensing images verify the effectiveness of the proposed method.