Abstract
Abstract. In the context of remote sensing image classification, Markov random fields (MRFs) have been used to combine both spectral and contextual information. The MRFs use a smoothing parameter to balance the contribution of the spectral versus spatial energies, which is often defined empirically. This paper proposes a framework to estimate the smoothing parameter using the probability estimates from support vector machines and the spatial class co-occurrence distribution. Furthermore, we construct a spatially weighted parameter to preserve the edges by using seven different edge detectors. The performance of the proposed methods is evaluated on two hyperspectral datasets recorded by the AVIRIS and ROSIS and a simulated ALOS PALSAR image. The experimental results demonstrated that the estimated smoothing parameter is optimal and produces a classified map with high accuracy. Moreover, we found that the Canny-based edge probability map preserved the contours better than others.
Highlights
Hyperspectral imaging sensors provide a huge amount of data with rich spatial, spectral and temporal resolution information
Tolpekin and Stein (2009) demonstrated a new smoothing parameter estimation technique for super-resolution mapping based on class separability, the neighbourhood system size and the configuration of class labels
In the development of our new smoothing parameter estimation framework, we denote an image by Y = Yi ∈ RB, i = 1, 2, · · ·, m, where B is a number of spectral channels, and m is a number of pixels
Summary
Hyperspectral imaging sensors provide a huge amount of data with rich spatial, spectral and temporal resolution information. This article presents a novel robust framework for the smoothing parameter estimation which is not dependent on assumptions of a specific statistical distribution of the image data (Section 2.1). This contextually adaptive smoothing parameter estimation method is proposed on the basis of the balance of spatial and spectral energies and the global spatial frequency distribution of a co-occurrence class label. For this purpose, we have introduced a new spectral energy change function and two new concepts called the class label co-occurrence matrix of the categories. By substitution (3- 5) in (2) we can write (2) as (6)
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: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
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.
