Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Improving linear classification using semi-supervised invertible manifold alignment

: Gross, Wolfgang; Espinosa, Nayeli; Becker, Merlin; Schreiner, Simon; Middelmann, Wolfgang


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Geoscience and Remote Sensing Society:
IGARSS 2018, IEEE International Geoscience and Remote Sensing Symposium. Proceedings : Observing, understanding and forecasting the dynamics of our planet, July 22-27, 2018, Valencia, Spain
Piscataway, NJ: IEEE, 2018
ISBN: 978-1-5386-7150-4
ISBN: 978-1-5386-7149-8
ISBN: 978-1-5386-7151-1
International Geoscience and Remote Sensing Symposium (IGARSS) <2018, Valencia>
Conference Paper
Fraunhofer IOSB ()
hyperspectral classification; nonlinear effect; mitigation; manifold alignment

Non-linear effects in hyperspectral data are the result of varying illumination conditions, angular dependencies of reflection, shadows and multiple scattering of incident light. Common classification algorithms like Spectral Angular Mapper (SAM) and Adaptive Coherence Estimator (ACE) struggle to produce good results under these conditions. In this paper, we evaluate our fast Semi-supervised Invertible Manifold Alignment, introduced in [1], on multiple commonly available hyperspectral remote sensing data sets. Additionally, we test it on our new benchmark data set for multitemporal analysis. We show that linear SAM classification on SIMA-transformed data is superior to linear classification on the original data in all cases. Also, SIMA-transformation with subsequent SAM classification produces comparable results to a multi-class Support Vector Machine (SVM), with the benefit of maintaining physical interpretability of the transformed data.