Tensor Discriminative Locality Alignment for Hyperspectral Image Spectral-Spatial Feature Extraction

In this paper, we propose a method for the dimensionality reduction (DR) of spectral-spatial features in hyperspectral images (HSIs), under the umbrella of multilinear algebra, i.e., the algebra of tensors. The proposed approach is a tensor extension of conventional supervised manifold-learning-base...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on geoscience and remote sensing Vol. 51; no. 1; pp. 242 - 256
Main Authors Liangpei Zhang, Lefei Zhang, Dacheng Tao, Xin Huang
Format Journal Article
LanguageEnglish
Published New York, NY IEEE 01.01.2013
Institute of Electrical and Electronics Engineers
Subjects
Applied geophysics
Classification
Earth sciences
Earth, ocean, space
Exact sciences and technology
Feature extraction
hyperspectral image (HSI)
Hyperspectral imaging
Internal geophysics
Optimization
remote sensing
Tensile stress
tensor
Vectors
hyperspectral image (HSI)
extension
accuracy
remote sensing
classification
extraction
tensor
collections
feature extraction
imagery
organization
reduction
Pixel
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a method for the dimensionality reduction (DR) of spectral-spatial features in hyperspectral images (HSIs), under the umbrella of multilinear algebra, i.e., the algebra of tensors. The proposed approach is a tensor extension of conventional supervised manifold-learning-based DR. In particular, we define a tensor organization scheme for representing a pixel's spectral-spatial feature and develop tensor discriminative locality alignment (TDLA) for removing redundant information for subsequent classification. The optimal solution of TDLA is obtained by alternately optimizing each mode of the input tensors. The methods are tested on three public real HSI data sets collected by hyperspectral digital imagery collection experiment, reflective optics system imaging spectrometer, and airborne visible/infrared imaging spectrometer. The classification results show significant improvements in classification accuracies while using a small number of features.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2012.2197860