27 December 2017 Multi-information fusion sparse coding with preserving local structure for hyperspectral image classification
Author Affiliations +
Abstract
The key question of sparse coding (SC) is how to exploit the information that already exists to acquire the robust sparse representations (SRs) of distinguishing different objects for hyperspectral image (HSI) classification. We propose a multi-information fusion SC framework, which fuses the spectral, spatial, and label information in the same level, to solve the above question. In particular, pixels from disjointed spatial clusters, which are obtained by cutting the given HSI in space, are individually and sparsely encoded. Then, due to the importance of spatial structure, graph- and hypergraph-based regularizers are enforced to motivate the obtained representations smoothness and to preserve the local consistency for each spatial cluster. The latter simultaneously considers the spectrum, spatial, and label information of multiple pixels that have a great probability with the same label. Finally, a linear support vector machine is selected as the final classifier with the learned SRs as input. Experiments conducted on three frequently used real HSIs show that our methods can achieve satisfactory results compared with other state-of-the-art methods.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Xiaohui Wei, Xiaohui Wei, Wen Zhu, Wen Zhu, Bo Liao, Bo Liao, Changlong Gu, Changlong Gu, Weibiao Li, Weibiao Li, } "Multi-information fusion sparse coding with preserving local structure for hyperspectral image classification," Journal of Applied Remote Sensing 11(4), 045016 (27 December 2017). https://doi.org/10.1117/1.JRS.11.045016 . Submission: Received: 26 July 2017; Accepted: 2 December 2017
Received: 26 July 2017; Accepted: 2 December 2017; Published: 27 December 2017
JOURNAL ARTICLE
22 PAGES


SHARE
Back to Top