Abstract
Abstract. The objective of this study was to improve the Markov Random Field (MRF) based Super Resolution Mapping (SRM) technique to account for the vague land-cover interpretations (class mixture and the intermediate conditions) in an urban area. The algorithm has been improved to integrate the fuzzy mean and fuzzy covariance measurements, to a MRF based SRM scheme to optimize the classification results. The technique was tested on a WORLDVIEW-2 data set, acquired over a highway construction area, in Colombo, Sri Lanka. Based on the visual interpretation of the image, three major land-cover types of this area were identified for the study; those were vegetation, soil and exposed grass and impervious surface with low medium and high albedo. The membership values for each pixel were determined from training samples through Spectral Angle Mapper (SAM) technique. The compulsory fuzzy mean and the covariance measurements were derived using these membership grades, and subsequently was applied in MRF based SRM technique. The primary reference data was generated using Maximum Likelihood Classification (MLC) performed on the same data which was resampled to 1m resolution. The scale factor was set to be (S) = 2, to generate SRM of 1m resolution. The smoothening parameter (λ) which balances the prior and likelihood energy terms were tested in the range from 0.3 to 0.9. SRM were generated using fuzzy MRF and the conventional MRF models respectively. Results suggest that the fuzzy integrated model has improved the results with an overall accuracy of 85.60% and kappa value of 0.78 between the optimal results and the reference data, while in the conventional case it was 77.81% of overall accuracy with kappa being 0.65. Among the two MRF models, fuzzy parameter integrated model shows the highest agreement with class fractions from the reference image with a smallest average _MAE (MAE, Mean Absolute Error) of 0.03.
Highlights
Pattern recognition using satellite imagery has been challenged by the urban land scape in establishing a precise relationship between the pattern and a class label
Experimental results of the Markov Random Field (MRF) based Super Resolution Mapping (SRM) with respect to several smoothness parameters (λ) using the fuzzy and the conventional class parameters are shown in the Figs. 3 and 4 respectively
When λ=1 the likelihood term is completely ignored in Eq (12) for a minimal posterior energy, which forces all the pixels to be classified to a single class
Summary
Pattern recognition using satellite imagery has been challenged by the urban land scape in establishing a precise relationship between the pattern and a class label. The rapid change of the urban land-cover categories within a small distance resulting similar entities at different locations, majority of landcover types being internally heterogeneous and intermediate conditions of the class boundaries make the urban landscape a vague entity (Wang, 1990; Wood and Foody, 1993) This situation on the ground makes a mix spectral signature within a pixel of a satellite image (Zhang and Foody, 2001). MRF have been potentially identified in Remote Sensing image classification with promising results, mainly due to its ability to integrate the contextual based information in to the classification scheme (Kasetkasem et al, 2005; Solberg et al, 1996) This practical applicability of MRF has been made possible by the equivalence between MRF and Gibbs distribution, established by the Hammersley-Clifford theorem (Li, 2009; Tso and Mather, 2009). In this study we propose a robust MRF model which integrates the fuzzy class descriptive statistics, to produce SRM with improved classification results
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
