Abstract
Sparse representation classification (SRC) is being widely applied to target detection in hyperspectral images (HSI). However, due to the problem in HSI that high-dimensional data contain redundant information, SRC methods may fail to achieve high classification performance, even with a large number of spectral bands. Selecting a subset of predictive features in a high-dimensional space is an important and challenging problem for hyperspectral image classification. In this paper, we propose a novel discriminant feature learning (DFL) method, which combines spectral and spatial information into a hypergraph Laplacian. First, a subset of discriminative features is selected, which preserve the spectral structure of data and the inter- and intra-class constraints on labeled training samples. A feature evaluator is obtained by semi-supervised learning with the hypergraph Laplacian. Secondly, the selected features are mapped into a further lower-dimensional eigenspace through a generalized eigendecomposition of the Laplacian matrix. The finally extracted discriminative features are used in a joint sparsity-model algorithm. Experiments conducted with benchmark data sets and different experimental settings show that our proposed method increases classification accuracy and outperforms the state-of-the-art HSI classification methods.
Highlights
In recent years, hyperspectral image (HSI) analysis has received an increasing amount of interest among the remote sensing community, such as military investigation, agriculture, mineralogy, surveillance, and chemical imaging
A number of statistical hypothesis testing techniques [9,10,11,12] have been proposed for target detection in HSI, such as the spectral matched filter (SMF), matched subspace detectors (MSDs) [13], adaptive subspace detectors (ASDs) [12], Reed-CXiaoli (RX) anomaly detector [14,15], kernel RX [16,17], and traditional Gaussian and linear mixture models
We propose a discriminant feature learning scheme for hyperspectral image classification based on sparse representation, which considers the spectral and spatial knowledge to achieve the low-dimensional representations of hyperspectral image data
Summary
Hyperspectral image (HSI) analysis has received an increasing amount of interest among the remote sensing community, such as military investigation, agriculture, mineralogy, surveillance, and chemical imaging. Each pixel in a hyperspectral image is captured from hyperspectral sensors containing hundreds of contiguous spectral channels (termed as bands) over a wide range of the electromagnetic spectrum This brings target classification advantages when identifying the target of interest in a hyperspectral scene by exploiting the spectral signatures of the materials. In cases where target information exists, these target detection algorithms usually try to match the target’s signature distribution to the suspect pixel and suppress the background. Chen et al [27] proposed the pixelwise-based SR technique for HSI target detection This detection technique is performed for each pixel in the test image independently, regardless of the spatial correlation of neighboring pixels. The joint SR [30,31,32] that incorporates interpixel correlation information of neighborhoods was proposed to further improve classification performance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
