Abstract
Combined techniques of sparse representation (SR) and low-rank representation (LRR) are commonly used for hyperspectral image (HSI) classification. Although they have the ability to capture the interclass representations of data for HSI classification, they ignore the adaptive key connectivity of the learned intraclass data representations in particular with the high-dimensional complex HSI data. It is well-known that the key connectivity of graph-based algorithms is crucial for subspace learning because of the guarantees of its good neighbors. For this purpose, a novel sparse and low-rank representation with key connectivity (SLRC) method is proposed for HSI classification. To be specific, the adaptive probability graph structure is developed to integrate the SR and LRR regularizations to formulate the SLRC model, which flexibly perform discriminative latent subspace construction and preserve the key connectivity of intraclass representations. Then, extensive experiments are executed based on three popular HSI datasets, which demonstrates that the SLRC method outperforms the other popular methods.
Highlights
H YPERSPECTRAL images (HSIs) provide detailed structural and spectral information because they comprise hundreds of narrow spectral bands [1]–[4], which can effectively capture the subtle differences between different materials and facilitate better land-cover classification
To address the hardness of the key connectivity in HSI analysis based on the CSRLRR techniques, motivated by [38] and [39], we propose a novel sparse and low-rank representation with key connectivity (SLRC) model for preserving key connectivity of intraclass representations in HSI classification based on CSRLRR techniques
In terms of overall accuracy (OA) and kappa coefficient (KC), the SLRC method achieves values of 98.86% and 98.70%, respectively, which are higher than those of the other methods, which verifies the effectiveness of this approach in HSI classification
Summary
H YPERSPECTRAL images (HSIs) provide detailed structural and spectral information because they comprise hundreds of narrow spectral bands [1]–[4], which can effectively capture the subtle differences between different materials and facilitate better land-cover classification. A natural idea is to combine the SR and LRR based regularization to obtain a balanced graph connectivity based on self-expressiveness property that automatically picks a few other points that are not necessarily close to it but that belong to the same subspace to recover the corresponding subspace for HSI classification. Different from the proposed adaptive models in [39], we utilize the balanced valuable representation vectors of underlying subspace between SR regularization and LRR regularization as intrinsic information to seek adaptive probabilistic connectivity between each pair of samples in the SLRC model. The intrinsic connectivity information associated with the adaptive probability graph structure is integrated to SR and DING et al.: SPARSE AND LOW-RANK REPRESENTATION WITH KEY CONNECTIVITY FOR HSI CLASSIFICATION.
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
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.
