Abstract | ||
---|---|---|
The classification of large areas consisting of multiple scenes is challenging regarding the handling of large and therefore mostly inhomogeneous data sets. Moreover, large data sets demand for computational efficient methods. We propose a method, which enables the efficient multi-class classification of large neighboring Landsat scenes. We use an incremental realization of the import vector machines, called I2VM, in combination with self-training to update an initial learned classifier with new training data acquired in the overlapping areas between neighboring Landsat scenes. We show in our experiments, that I2VM is a suitable classifier for large area land cover classification. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICCVW.2011.6130249 | ICCV Workshops |
Keywords | DocType | Volume |
terrain mapping,scenes classification,land cover classification,data acquisition,image classification,geophysical image processing,incremental import vector machines,natural scenes,inhomogeneous data sets,training data acquisition,neighboring landsat scenes,support vector machines,multi class classification,training data,remote sensing,vectors,earth,satellites,kernel | Conference | 2011 |
Issue | ISBN | Citations |
1 | 978-1-4673-0062-9 | 1 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ribana Roscher | 1 | 46 | 8.10 |
Björn Waske | 2 | 435 | 24.75 |
Wolfgang Förstner | 3 | 154 | 12.23 |