Automatic land- cover update approach integrating iterative training sample selection and a Markov Random Field model

Land-cover updating from remote-sensing data is an effective means of obtaining timely land-cover information. An automatic approach integrating iterative training sample selection (ITSS) and a Markov Random Field (MRF) model is proposed in this study to overcome the land-cover update problem when no previous remote-sensing data corresponding to the land-cover data are available. A case study in the Beijing region indicates that ITSS can effectively select reliable training samples based on historical land-cover data and that ITSS with MRF can achieve satisfactory land-cover update results (overall classification accuracy: 83.1%). The MRF model can effectively reduce salt-and-pepper noise and improve overall accuracy by approximately 6%. The proposed approach is completely unsupervised and has no strict requirements for newly acquired remote-sensing data for land-cover updating.