Exploring Structural Consistency in Graph Regularized Joint Spectral-Spatial Sparse Coding for Hyperspectral Image Classification

View/ Open
Author(s)
Liu, Changhong
Zhou, Jun
Liang, Jie
Qian, Yuntao
Li, Hanxi
Gao, Yongsheng
Year published
2017
Metadata
Show full item recordAbstract
In hyperspectral image classification, both spectral and spatial data distributions are important in describing and identifying different materials and objects in the image. Furthermore, consistent spatial structures across bands can be useful in capturing inherent structural information of objects. These imply that three properties should be considered when reconstructing an image using sparse coding methods. First, the distribution of different ground objects leads to different coding coefficients across the spatial locations. Second, local spatial structures change slightly across bands due to different reflectance ...
View more >In hyperspectral image classification, both spectral and spatial data distributions are important in describing and identifying different materials and objects in the image. Furthermore, consistent spatial structures across bands can be useful in capturing inherent structural information of objects. These imply that three properties should be considered when reconstructing an image using sparse coding methods. First, the distribution of different ground objects leads to different coding coefficients across the spatial locations. Second, local spatial structures change slightly across bands due to different reflectance properties of various object materials. Finally and more importantly, some sort of structural consistency shall be enforced across bands to reflect the fact that the same object appears at the same spatial location in all bands of an image. Based on these considerations, we propose a novel joint spectral-spatial sparse coding model that explores structural consistency for hyperspectral image classification. For each band image, we adopt a sparse coding step to reconstruct the structures in the band image. This allows different dictionaries be generated to characterize the band-wise image variation. At the same time, we enforce the same coding coefficients at the same spatial location in different bands so as to maintain consistent structures across bands. To further promote the discriminating power of the model, we incorporate a graph Laplacian sparsity constraint into the model to ensure spectral consistency in the dictionary generation step. Experimental results show that the proposed method outperforms some state-of-the-art spectral-spatial sparse coding methods.
View less >
View more >In hyperspectral image classification, both spectral and spatial data distributions are important in describing and identifying different materials and objects in the image. Furthermore, consistent spatial structures across bands can be useful in capturing inherent structural information of objects. These imply that three properties should be considered when reconstructing an image using sparse coding methods. First, the distribution of different ground objects leads to different coding coefficients across the spatial locations. Second, local spatial structures change slightly across bands due to different reflectance properties of various object materials. Finally and more importantly, some sort of structural consistency shall be enforced across bands to reflect the fact that the same object appears at the same spatial location in all bands of an image. Based on these considerations, we propose a novel joint spectral-spatial sparse coding model that explores structural consistency for hyperspectral image classification. For each band image, we adopt a sparse coding step to reconstruct the structures in the band image. This allows different dictionaries be generated to characterize the band-wise image variation. At the same time, we enforce the same coding coefficients at the same spatial location in different bands so as to maintain consistent structures across bands. To further promote the discriminating power of the model, we incorporate a graph Laplacian sparsity constraint into the model to ensure spectral consistency in the dictionary generation step. Experimental results show that the proposed method outperforms some state-of-the-art spectral-spatial sparse coding methods.
View less >
Journal Title
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Subject
Photogrammetry and Remote Sensing
Physical Geography and Environmental Geoscience
Artificial Intelligence and Image Processing
Geomatic Engineering