Hyperspectral image feature extraction method based on 3-D wavelet transform and sparse tensor

Abstract

The invention discloses a hyperspectral image feature extraction method based on 3-D wavelet transform and a sparse tensor. The hyperspectral image feature extraction method includes step (1), balancing influence of data on feature extraction distinguishing according to a data normalization method; step (2), extracting spectral domain and spatial domain features from the normalized data by 3-D discrete wavelet transform; step (3), keeping good structural dependence between the features by expressing wavelet transform features as a second-order feature tensor form; step (4), achieving feature sparsification according to a sparse tensor distinguishing method; step (5), re-expressing the features subjected to sparsification as a vector form. By the hyperspectral image feature extraction method, classification accuracy of a whole classification system can be improved effectively.

Description

Technical field [0001] The invention belongs to the field of hyperspectral image data processing and application, and in particular relates to a hyperspectral image feature extraction method based on 3-D wavelet transform and sparse tensor. Background technique [0002] Hyperspectral imaging integrates the spatial information and spectral information of the target. While imaging the target space, it collects tens or even hundreds of continuous waveband spectral data for each spatial pixel. Hyperspectral images have outstanding advantages in recognition and accurate classification, and have been widely successfully used in medical diagnosis, agricultural detection, mineral detection, environmental monitoring and other fields. [0003] Hyperspectral data has problems such as large amount of data, high redundancy, and dimensionality disaster. To achieve the problem of hyperspectral image classification, it is first necessary to extract discriminative features. Existing feature extrac...

AI Technical Summary

Problems solved by technology

Existing feature extraction methods, such as DWT (Discrete Wavelet Transform), EMPs (Extended morphological profiles), EAPs (Extended attribute profiles) and other methods, perform feature transformation on all bands or several principal components of hyperspectral images, and then convert the obtained The features of the feature are integrated into a long vector, which not only causes the dimension of the feature vector to be too high, but also loses a lot of structural information.

Images