Wavelet-based multicomponent denoising on GPU to improve the classification of hyperspectral images

Supervised classi cation allows handling a wide range of remote sensing hyperspectral applications. Enhancing the spatial organization of the pixels over the image has proven to be bene cial for the interpretation of the image content, thus increasing the classi cation accuracy. Denoising in the spatial domain of the image has been shown as a technique that enhances the structures in the image. This paper proposes a multi-component denoising approach in order to increase the classi cation accuracy when a classi cation method is applied. It is computed on multicore CPUs and NVIDIA GPUs. The method combines feature extraction based on a 1Ddiscrete wavelet transform (DWT) applied in the spectral dimension followed by an Extended Morphological Pro le (EMP) and a classi er (SVM or ELM). The multi-component noise reduction is applied to the EMP just before the classi cation. The denoising recursively applies a separable 2D DWT after which the number of wavelet coecients is reduced by using a threshold. Finally, inverse 2D-DWT lters are applied to reconstruct the noise free original component. The computational cost of the classi ers as well as the cost of the whole classi cation chain is high but it is reduced achieving real-time behavior for some applications through their computation on NVIDIA multi-GPU platforms.

keywords: Land cover classi cation, Hyperspectral analysis, Wavelet transform, Denoising, Spectral-spatial processing, High-Performance computing, Multi-thread, Multi-GPU.