In this paper, the problem of the spatial-spectral classification of very high-resolution optical images is addressed using a kernel- A nd region-based approach. A novel method based on integrating region-based or object-based information into a kernel machine is developed. A Gaussian process model is used to characterize each segment in a segmentation map and to define a region-based admissible kernel accordingly. This kernel is combined with a marker-controlled watershed segmentation that incorporates scale adaptivity. Spatialspectral fusion capabilities are also ensured by combining the resulting classification method with composite kernels.
Very high resolution optical image classification using watershed segmentation and a region-based kernel / De Giorgi, A.; Moser, G.; Poggi, G.; Scarpa, G.; Serpico, S. B.. - (2018), pp. 1312-1315. (Intervento presentato al convegno 38th Annual IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2018 tenutosi a Valencia (Spain) nel 2018) [10.1109/IGARSS.2018.8518526].
Very high resolution optical image classification using watershed segmentation and a region-based kernel
Poggi G.;Scarpa G.;
2018
Abstract
In this paper, the problem of the spatial-spectral classification of very high-resolution optical images is addressed using a kernel- A nd region-based approach. A novel method based on integrating region-based or object-based information into a kernel machine is developed. A Gaussian process model is used to characterize each segment in a segmentation map and to define a region-based admissible kernel accordingly. This kernel is combined with a marker-controlled watershed segmentation that incorporates scale adaptivity. Spatialspectral fusion capabilities are also ensured by combining the resulting classification method with composite kernels.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
