Hyperspectral unmixing on GPUs and multi-core processors : a comparison

Por: Bernabé, Sergio ... [et al.].
Colaborador(es): Sánchez, Sergio | Plaza, Antonio | López, Sebastián | Benediktsson, Jón Atli | Sarmiento, Roberto.
Tipo de material: materialTypeLabelArtículoTema(s): Satélites artificiales en detección a distancia | Procesamiento óptico de datos | Reconocimiento de edificios | Sistemas de imágenes | Procesamiento de imágenes | Análisis espectral | Espectrómetros | Análisis espectral En: Journal of selected topics in applied earth observations and remote sensing Vol.6, núm.3 (June, 2013), pp. 1386-1398Resumen: One of the main problems in the analysis of remotely sensed hyperspectral data cubes is the presence of mixed pixels, which arise when the spatial resolution of the sensor is not able to separate spectrally distinct materials. Due to this reason, spectral unmixing has become one of the most important tasks for hyperspectral data exploitation. However,unmixing algorithms can be computationally very expensive, a fact that compromises their use in applications under real-time constraints. For this purpose, in this paper we develop two efficient implementations of a full hyperspectral unmixing chain on two different kinds of high performance computing architectures: graphics processing units (GPUs) and multi-core processors
Tipo de ítem Biblioteca de origen Colección Signatura Vol info Copia número Estado Fecha de vencimiento Código de barras Reserva de ejemplares
Revista Revista Campus II
Hemeroteca PP-2 550 I592j (Navegar estantería) Vol.6, núm.3 (June, 2013) Ej. 1 Disponible R132727
Reservas Totales: 0

CAMPUS II

One of the main problems in the analysis of remotely sensed hyperspectral data cubes is the presence of mixed pixels, which arise when the spatial resolution of the sensor is not able to separate spectrally distinct materials. Due to this reason, spectral unmixing has become one of the most important tasks for hyperspectral data exploitation. However,unmixing algorithms can be computationally very expensive, a fact that compromises their use in applications under real-time constraints. For this purpose, in this paper we develop two efficient implementations of a full hyperspectral unmixing chain on two different kinds of high performance computing architectures: graphics processing units (GPUs) and multi-core processors