Abstract
The original Hyperspectral image (HSI) has different degrees of Hughes phenomenon and mixed noise, leading to the decline of classification accuracy. To make full use of the spatial-spectral joint information of HSI and improve the classification accuracy, a novel dual feature extraction framework joint transform domain-spatial domain filtering based on multi-scale-superpixel-dimensionality reduction (LRS-HRFMSuperPCA) is proposed. Our framework uses the low-rank structure and sparse representation of HSI to repair the unobserved part of the original HSI caused by noise and then denoises it through a block-matching 3D algorithm. Next, the dimension of the reconstructed HSI is reduced by principal component analysis (PCA), and the dimensions of the reduced images are segmented by multi-scale entropy rate superpixels. All the principal component images with superpixels are projected into the reconstructed HSI in parallel. Secondly, PCA is once again used to reduce the dimension of all HSIs with superpixels in scale with hyperpixels. Moreover, hierarchical domain transform recursive filtering is utilized to obtain the feature images; ultimately, the decision fusion strategy based on a support vector machine (SVM) is used for classification. According to the Overall Accuracy (OA), Average Accuracy (AA) and Kappa coefficient on the three datasets (Indian Pines, University of Pavia and Salinas), the experimental results have shown that our proposed method outperforms other state-of-the-art methods. The conclusion is that LRS-HRFMSuperPCA can denoise and reconstruct the original HSI and then extract the space-spectrum joint information fully.
Highlights
Hyperspectral image (HSI) uses numerous continuous narrow-band electromagnetic wave bands to image the surface species and obtain rich joint information of the space-spectrum
The conclusion is that LRS-HRFMSuperPCA can denoise and reconstruct the original HSI and extract the space-spectrum joint information fully
Compared to other HSI classification algorithms, we propose to integrate the new joint feature extraction framework of spatial domain filtering and transform domain filtering(LRS-HRF) into the MSuperPCA
Summary
HSI uses numerous continuous narrow-band electromagnetic wave bands to image the surface species and obtain rich joint information of the space-spectrum. With the rapid development of HSI processing and analysis in recent years, HSI classification technology is extensively utilized in agriculture [1], environmental detection [2], marine monitoring [3], and other fields; considering the effects of imaging sensor breakdown [4], environmental pollution [5], and other factors, the obtained HSI has mixed noise [6,7,8,9] that reduces the classification accuracy. Tu et al [7] proposed a kernel entropy component analysis (KECA)-based method for noisy label detection that can remove noisy labels for the PaviaU with 50 true samples and 10 noisy labels per class, KECA obtains. Proposed a spectral-spatial classification of HSI based on low-rank decomposition, by removing the sparse part, the LRD-NWFE-GC [8] obtains 92.3% on Indian Pines even if the training sample is small.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.