Abstract

We propose a context guided belief propagation (BP) algorithm to perform high spatial resolution multispectral imagery (HSRMI) classification efficiently utilizing superpixel representation. One important characteristic of HSRMI is that different land cover objects possess a similar spectral property. This property is exploited to speed up the standard BP (SBP) in the classification process. Specifically, we leverage this property of HSRMI as context information to guide messages passing in SBP. Furthermore, the spectral and structural features extracted at the superpixel level are fed into a Markov random field framework to address the challenge of low interclass variation in HSRMI classification by minimizing the discrete energy through context guided BP (CBP). Experiments show that the proposed CBP is significantly faster than the SBP while retaining similar performance as compared with SBP. Compared to the baseline methods, higher classification accuracy is achieved by the proposed CBP when the context information is used with both spectral and structural features.

© 2015 Optical Society of America

Supervised spatio-spectral classification of fused images using superpixels

Karen Sanchez, Carlos Hinojosa, and Henry Arguello
Appl. Opt. 58(7) B9-B18 (2019)

Use of customizing kernel sparse representation for hyperspectral image classification

Bin Qi, Chunhui Zhao, and Guisheng Yin
Appl. Opt. 54(4) 707-716 (2015)

C-3SPCD: coded aperture similarity constrained design for spatio-spectral classification of single-pixel measurements

Carlos Hinojosa, Karen Sanchez, Hans Garcia, and Henry Arguello
Appl. Opt. 61(8) E21-E32 (2022)

Hyperspectral remote sensing image classification based on random average band selection and an ensemble kernel extreme learning machine

Ba Tuan Le and Thai Thuy Lam Ha
Appl. Opt. 59(13) 4151-4157 (2020)

Dynamic descriptors for contextual classification of remotely sensed hyperspectral image data analysis

Wun C. Chiou
Appl. Opt. 23(21) 3889-3892 (1984)