Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery.pdfVIP

Remote Sensing of Environment 191 (2017) 342–358 Contents lists available at ScienceDirect Remote Sensing of Environment journal homepage: /locate/rse Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide ?eld of view imagery Zhiwei Li a, Huanfeng Shen a,b,c,?, Huifang Li a,?, Guisong Xia d, Paolo Gamba e, Liangpei Zhang b,d a School of Resource and Environmental Sciences, Wuhan University, Wuhan, China b Collaborative Innovation Center for Geospatial Technology, Wuhan, China c Key Laboratory of Geographic Information System, Ministry of Education, Wuhan University, Wuhan, China d State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China e Department of Electronics, University of Pavia, Pavia, Italy article info Article history: Received 15 July 2016 Received in revised form 16 January 2017 Accepted 21 January 2017 Available online 5 February 2017 Keywords: Cloud detection Cloud shadow GF-1 Multiple features MFC abstract The wide ?eld of view (WFV) imaging system onboard the Chinese GaoFen-1 (GF-1) optical satellite has a 16-m resolution and four-day revisit cycle for large-scale Earth observation. The advantages of the high temporal-spatial resolution and the wide ?eld of view make the GF-1 WFV imagery very popular. However, cloud cover is an inevitable problem in GF-1 WFV imagery, which in?uences its precise application. Accurate cloud and cloud shadow detection in GF-1 WFV imagery is quite dif?cult due to the fact that there are only three visible bands and one near-infrared band. In this paper, an automatic multi-feature combined (MFC) method is proposed for cloud and cloud shadow detection in GF-1 WFV imagery. The MFC algorithm ?rst implements threshold segmentation based on the spectral features and mask re?nement based on guided ?ltering to generate a preliminary cloud mask. The geometric features are then used in combination with the texture features to improve the cloud detect