Spectral-Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random Fields

• Published in: IEEE transactions on geoscience and remote sensing Vol. 50; no. 3; pp. 809 - 823
• Main Authors: Jun Li, Bioucas-Dias, J. M., Plaza, A.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.2012; Institute of Electrical and Electronics Engineers
• Subjects: Applied geophysics; Earth sciences; Earth, ocean, space; Exact sciences and technology; Hyperspectral image segmentation; Hyperspectral imaging; Image segmentation; Internal geophysics; Labeling; Logistics; Markov random field (MRF); multinomial logistic regression (MLR); Optimization; subspace projection method; Training; algorithms; probability; Markov random field (MRF); subspace projection method; classification; expansion; Hyperspectral image segmentation; optimization; regression; imagery; noise; segmentation; projection; performances; frame structure; Pixel; multinomial logistic regression (MLR)
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2011.2162649

This paper introduces a new supervised segmentation algorithm for remotely sensed hyperspectral image data which integrates the spectral and spatial information in a Bayesian framework. A multinomial logistic regression (MLR) algorithm is first used to learn the posterior probability distributions from the spectral information, using a subspace projection method to better characterize noise and highly mixed pixels. Then, contextual information is included using a multilevel logistic Markov-Gibbs Markov random field prior. Finally, a maximum a posteriori segmentation is efficiently computed by the min-cut-based integer optimization algorithm. The proposed segmentation approach is experimentally evaluated using both simulated and real hyperspectral data sets, exhibiting state-of-the-art performance when compared with recently introduced hyperspectral image classification methods. The integration of subspace projection methods with the MLR algorithm, combined with the use of spatial-contextual information, represents an innovative contribution in the literature. This approach is shown to provide accurate characterization of hyperspectral imagery in both the spectral and the spatial domain.