Loading...
Please wait, while we are loading the content...
Similar Documents
Suitability of Markov Random Field-Based Method for Super-Resolution Land Cover Mapping
| Content Provider | Semantic Scholar |
|---|---|
| Author | Kassaye, Rahel Hailu |
| Copyright Year | 2013 |
| Abstract | Super-resolution mapping (SRM) works by dividing the coarse pixel into sub-pixels and assign the class proportion estimated by subpixel classification to each corresponding sub-pixels then the class labelling is optimized based on the principle of spatial dependency. Among the existing SRM techniques Markov random field (MRF)based SRM is one of the most recently introduced technique. This study attempts to assess the suitability of the technique for superresolution land cover mapping. The spatial contextual smoothness constraint and spectral information were modelled with prior energy and the likelihood energy function respectively. These two energy functions were balanced with a smoothing parameter. Parameterization was done using the synthetic data sets and the effect of several factors on the quality of SRM was observed. The main findings in this study are: increasing the neighbourhood size while increasing scale factor enables to keep the Markovian property and the variability of optimal smoothing parameter in relation to the class separability. The appropriate setting of the optimal smoothing parameter can give a reasonable accuracy even for classes with low separability. The research result from both data sets proof the suitability of the method for super-resolution land cover mapping. |
| Starting Page | 1 |
| Ending Page | 5 |
| Page Count | 5 |
| File Format | PDF HTM / HTML |
| DOI | 10.4172/2327-4581.S1-012 |
| Volume Number | 2014 |
| Alternate Webpage(s) | http://www.itc.nl/library/papers_2006/msc/gfm/hailu.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
