A combined object-based segmentation and support vector machines approach for classification of Tiangong-01 hyperspectral urban data


Traditional hyperspectral classification methods based on per-pixel spectral or texture features fail to take account of spatial structure and spatial correlation characteristics. In order to overcome this problem, a mixed classification method is proposed which incorporates spatial information by fusion of object-based segmentation with pixel-wise… (More)
DOI: 10.1109/IGARSS.2014.6946797


1 Figure or Table

Slides referencing similar topics