Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Transformation of hyperspectral data to improve classification by mitigating nonlinear effects

: Gross, Wolfgang; Wuttke, Sebastian; Middelmann, Wolfgang

Fulltext urn:nbn:de:0011-n-3666367 (2.6 MByte PDF)
MD5 Fingerprint: b32864c6fb6d32b57d96c117fc2efc36
Created on: 18.11.2015

Institute of Electrical and Electronics Engineers -IEEE-:
7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015 : 2-5 June 2015, Tokyo, Japan
Piscataway, NJ: IEEE, 2015
ISBN: 978-1-4673-9015-6
ISBN: 978-1-4673-9014-9
ISBN: 978-1-4673-9016-3
Workshop on Hyperspectral Image and Signal Processing - Evolution in Remote Sensing (WHISPERS) <7, 2015, Tokyo>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()
hyperspectral; data transformation; mitigating nonlinear effects; supervised classification

Non-linear effects in hyperspectral data are caused by varying illumination conditions, different viewing angles or multiple scattering of the incident light. These effects interfere with commonly used data analysis procedures. Manifold learning procedures are slow and require certain assumptions about the data structure that do not necessarily hold in real hyperspectral data. In this paper, a transformation is proposed that uses neighborhood distances to track the nonlinear structures of multiple classes simultaneously. The transformation is evaluated using a hyperspectral data set containing nonlinearities. A classification is performed and the results on the original and the transformed data are compared.