Parallel real-time virtual dimensionality estimation for hyperspectral images

One of the most important tasks in hyperspectral imaging is the estimation of the number of endmembers in a scene, where the endmembers are the most spectrally pure components. The high dimensionality of hyperspectral data makes this calculation computationally expensive. In this paper, we present several new real-time implementations of the well-known Harsanyi–Farrand–Chang method for virtual dimensionality estimation. The proposed solutions exploit multi-core processors and graphic processing units for achieving real-time performance of this algorithm, together with better performance than other works in the literature. Our experimental results are obtained using both synthetic and real images. The obtained processing times show that the proposed implementations outperform other hardware-based solutions.