Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXVIII-4/W19, 365-368, 2011
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XXXVIII-4-W19/365/2011/
doi:10.5194/isprsarchives-XXXVIII-4-W19-365-2011
© Author(s) 2011. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
10 Sep 2012
ENDMEMBER EXTRACTION FOR HYPERSPECTRAL IMAGES USING WATERSHED AND NORMALIZED CUTS
H. Xu1, B. Tian2, and F. Liu3 1College of Resource Environment and Tourism, Capital Normal University, Beijing, China
2Center for Earth Observation and Digital Earth Chinese Academy of Sciences No.9 Dengzhuang South Road, Haidian District, Beijing 100094, China
3C#416 Office,P.O.Box 9718, No. 20 Datun Road, Olympic Science & Technology Park of CAS, Beijing 100101, China
Keywords: remote sensing images segmentation; watershed transform; normalized cut; endmember extraction; spatial-spectral; hyperspectral data Abstract. Endmember extraction integrated with spatial information has been concerned on some research recently. In this paper we studies an improved endmember extraction method with spatial preprocessing module which use watershed with normalized cuts to avoid over- segmentation and produce accurate results from spectral mixture analysis. The spatial-spectral endmember extraction method which used the advantages of image segmentation generates the preliminary results and provides important knowledge for future research.
Conference paper (PDF, 608 KB)


Citation: Xu, H., Tian, B., and Liu, F.: ENDMEMBER EXTRACTION FOR HYPERSPECTRAL IMAGES USING WATERSHED AND NORMALIZED CUTS, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XXXVIII-4/W19, 365-368, doi:10.5194/isprsarchives-XXXVIII-4-W19-365-2011, 2011.

BibTeX EndNote Reference Manager XML