Investigação sobre métodos para redução da dimensionalidade dos dados em imagens hiperespectrais

In the present study, we propose a new simple approach to reduce the data dimensionality in hyperspectral image data. The basic assumption here consists in assuming that a pixel's curve of spectral response, as defined in the spectral space by the recorded digital numbers (DN's) at the available spectral bands, can be segmented and each segment can be replaced by a smaller number of statistics: mean and variance, describing the main characteristics of a pixel's spectral response. It is expected that this procedure can be accomplished without significant loss of information. The DN's at every spectral band are here used to calculate a few statistics that will then replace them in a classifier. For the pixel's spectral curve segmentation, we propose tree sub-optimal algorithms that are easy to implement and also computationally efficient. Using a top-down strategy, the length of the segments along the spectral curves can or not be adjusted sequentially. Experiments using a parametric classifier are performed on an AVIRIS data set. Encouraging results have been obtained in terms of classification accuracy and execution time, suggesting the effectiveness of the proposed algorithms. Palavras-chave: feature extraction, feature selection, data dimensionality reduction, hyperspectral image data, remote sensing, extracao de feicoes, selecao de feicoes, reducao da dimensionalidade, imagens hiperespectrais, sensoriamento remoto.