cad a22 4500 316949418 20181103043303.0 cr unu---uuuuu 140620e19980710xx s 100 0 eng 10.5167/uzh-96578 doi 10.1109/IGARSS.1998.699616 doi (ZORA)oai:www.zora.uzh.ch:96578 910 ddc Kneubühler Mathias Comparison of different approaches of selecting endmembers to classify agricultural land by means of hyperspectral data (DAIS7915) [Elektronische Daten] [Mathias Kneubühler, Michael E Schaepman, Tobias W Kellenberger] openAccess eu-repo A major problem in classification of hyperspectral datasets is the reliable selection of reference spectra to classify heterogeneous vegetated areas. In this work, different approaches of end-member collection for spectral unmixing of hyperspectral data are presented, evaluated and compared to each other. The selected methods include high resolution ground spectroradiometric measurements, a scene based approach and modelling of the end-member spectra using a SVAT (soil-vegetation-atmosphere-transfer) approach. The presented methods are discussed and verified with an extensive ground truth collected in the observed area. Institute of Geography zora Schaepman Michael E. joint author Kellenberger Tobias W. joint author IGARSS 1998, Seattle, USA, 6 July 1998 - 10 July 1998 s.n., 1998 888-890 0780344030 https://www.zora.uzh.ch/id/eprint/96578/1/Kneubuehler_1998_IGARSS98.pdf text/html WWW-Backlink auf das Repository Onlinezugriff via WWW text/html http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=699616&tag=1 ZORA 1 Conference or Workshop Item NonPeerReviewed zora ZORA 856 40 https://www.zora.uzh.ch/id/eprint/96578/1/Kneubuehler_1998_IGARSS98.pdf text/html WWW-Backlink auf das Repository ZORA 856 42 Onlinezugriff via WWW text/html http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=699616&tag=1 ZORA 100 1- Kneubühler Mathias ZORA 700 1- Schaepman Michael E. joint author ZORA 700 1- Kellenberger Tobias W. joint author ZORA 773 0- IGARSS 1998, Seattle, USA, 6 July 1998 - 10 July 1998 s.n., 1998 888-890 0780344030 BK010053 XK010053 XK010000 ZORA ZORA ZORA Conference or Workshop Item openAccess