ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 263-270, 2016
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-7/263/2016/
doi:10.5194/isprs-annals-III-7-263-2016
 
07 Jun 2016
TASK-DEPENDENT BAND-SELECTION OF HYPERSPECTRAL IMAGES BY PROJECTION-BASED RANDOM FORESTS
R. Hänsch and O. Hellwich Dept. of Computer Vision and Remote Sensing, Technische Universität Berlin, Germany
Keywords: Band selection, classification, hyperspectral images, Random Forests Abstract. The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limited to a subset of all available data dimensions which is found by band selection techniques or other methods of dimensionality reduction. This work applies Projection-Based Random Forests to hyperspectral images, which not only overcome the need of an explicit feature extraction, but also provide mechanisms to automatically select spectral bands that contain original (i.e. non-redundant) as well as highly meaningful information for the given classification task. The proposed method is applied to four challenging hyperspectral datasets and it is shown that the effective number of spectral bands can be considerably limited without loosing too much of classification performance, e.g. a loss of 1 % accuracy if roughly 13 % of all available bands are used.
Conference paper (PDF, 4964 KB)


Citation: Hänsch, R. and Hellwich, O.: TASK-DEPENDENT BAND-SELECTION OF HYPERSPECTRAL IMAGES BY PROJECTION-BASED RANDOM FORESTS, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 263-270, doi:10.5194/isprs-annals-III-7-263-2016, 2016.

BibTeX EndNote Reference Manager XML