A comparative study of multiscale representations for spatial-spectral classification of hyperspectral imagery
Abstract Hyperspectral remote sensors acquire data coming from hundreds of narrow bands through the electromagnetic spectrum; this allows the terrestrial and maritime surfaces to be characterized for Earth observation. Hyperspectral image processing requires algorithms that combine spatial and spectral information. One way to take full advantage of spatial-spectral data within hyperspectral imagery is to use multiscale representations. A multiscale representation generates a family of images were fine details are systematically removed. This paper compares two multiscale representation approaches in order to improve the classification of hyperspectral imagery. The first approach is based on nonlinear diffusion, which obtains a multiscale representation by successive filtering. The second is based on binary partition tree, an approach inspired in region growing. The comparison is performed using a real hyperspectral image and a supper vector machine classifier. Both representation approaches allowed the classification of hyperspectral imagery to be improved. However, nonlinear diffusion results surpassed those obtained using binary partition tree.
| Main Author: | |
|---|---|
| Format: | Digital revista |
| Language: | English |
| Published: |
Universidad Nacional de Colombia
2017
|
| Online Access: | http://www.scielo.org.co/scielo.php?script=sci_arttext&pid=S0012-73532017000100129 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|