RT Dissertation/Thesis
T1 Efficient multitemporal change detection techniques for hyperspectral images on GPU
A1 López Fandiño, Javier
K1 Change detection
K1 Remote sensing
K1 Hyperspectral imaging
K1 Graphics processing unit
AB Hyperspectral images contain hundreds of reflectance values for each pixel.Detecting regions of change in multiple hyperspectral images of the samescene taken at different times is of widespread interest for a large number ofapplications. For remote sensing, in particular, a very common application island-cover analysis. The high dimensionality of the hyperspectral imagesmakes the development of computationally efficient processing schemescritical. This thesis focuses on the development of change detectionapproaches at object level, based on supervised direct multidateclassification, for hyperspectral datasets. The proposed approaches improvethe accuracy of current state of the art algorithms and their projection ontoGraphics Processing Units (GPUs) allows their execution in real-timescenarios.
YR 2018
FD 2018
LK http://hdl.handle.net/10347/17281
UL http://hdl.handle.net/10347/17281
LA eng
DS Minerva
RD 22 abr 2026