Automatic land- cover update approach integrating iterative training sample selection and a Markov Random Field model
作者:Jia, K (Jia, Kun)[ 1,2 ] ; Liang, SL (Liang, Shunlin)[ 1,2,3 ] ; Wei, XQ (Wei, Xiangqin)[ 4 ] ; Zhang, L (Zhang, Lei)[ 4 ] ; Yao, YJ (Yao, Yunjun)[ 1,2 ] ; Gao, S (Gao, Shuai)[ 4 ]
REMOTE SENSING LETTERS
卷: 5  期: 2  页: 148-156
DOI: 10.1080/2150704X.2014.889862
出版年: FEB 1 2014

摘要
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.

通讯作者地址: Wei, XQ (通讯作者)
Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China.
地址:
[ 1 ] Beijing Normal Univ, State Key Lab Remote Sensing Sci, Beijing 100875, Peoples R China
[ 2 ] Beijing Normal Univ, Coll Global Change & Earth Syst Sci, Beijing 100875, Peoples R China
[ 3 ] Univ Maryland, Dept Geog Sci, College Pk, MD 20742 USA
[ 4 ] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, Beijing 100101, Peoples R China