Abstract
Hyperspectral images (HSIs) consist of hundreds of spectral bands, which can be used to precisely characterize different land cover types. However, an HSI has redundant information and is prone to the “dimensionality curse.” Therefore, it is necessary to reduce redundant information through dimensionality reduction (DR), given that different dimensions contain unique primary feature information, and the feature information is complementary. Accordingly, a new feature extraction method based on multidimensional spectral regression whitening (M-SRW) is proposed, which reduces HSI to different dimensions and reconstructs it for feature extraction. The proposed method consists of the following steps: First, the original HSI is superpixel segmented by the entropy rate segmentation algorithm. Second, SRW is performed in each superpixel block to reduce the dimension of each superpixel block to a different dimension. Third, superpixel blocks of the same dimension are combined to obtain the reconstructed HSI. Finally, the support vector machine is utilized to classify the reconstructed HSI of different dimensions, and majority voting decision fusion is used to obtain the final classification result map. Experiments on three public hyperspectral data sets demonstrated that the proposed M-SRW method is superior to several state-of-the-art feature extraction approaches in terms of classification accuracy.
Highlights
Given that different dimensions of Hyperspectral images (HSIs) contain unique primary feature information, and feature information is complementary, we propose a new HSI feature extraction method based on dimensionality reduction (DR) and multi-dimensional spectral regression whitening (M-SRW) which can efficiently use local superpixel block and multi-dimensional spectral information complementary
We evaluated the performance of our method under the scenario of a small number of training samples, by comparing our method with some state-of-art algorithms, including support vector machine (SVM) [45], sparse representation classifier (SRC) [47], extreme learning machine (ELM) [48], joint sparse representation classifier (JSRC) [49], extended morphological profiles (EMP) [50], edge-preserving filtering (EPF) [51], and image fusion and recursive filtering (IFRF) [52], to demonstrates the superiority and effectiveness of our proposed framework compared with other algorithms
This paper proposes a novelty feature extraction method for HSI based on M-SRW dimensionality reduction
Summary
Given that different dimensions of HSIs contain unique primary feature information, and feature information is complementary, we propose a new HSI feature extraction method based on DR and multi-dimensional spectral regression whitening (M-SRW) which can efficiently use local superpixel block and multi-dimensional spectral information complementary. The primary contributions of this paper are as follows: 1) Compared with the traditional feature extraction method, the M-SRW method proposed in this paper pays more attention to the detailed information of HSI in the superpixel block in the model. This local information is retained more effectively inherited local structure of the original data, to reduce missing critical information.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have