Learning-based superresolution land cover mapping
Super-resolution mapping (SRM) is a technique for generating a fine spatial resolution land cover map from coarse spatial resolution fraction images estimated by soft classification. The prior model used to describe the fine spatial resolution land cover pattern is a key issue in SRM. Here, a novel...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers
2016
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/32958/ |
| _version_ | 1848794528012566528 |
|---|---|
| author | Ling, Feng Zhang, Yihang Foody, Giles M. Li, Xiaodong Zhang, Xiuhua Fang, Shiming Li, Wenbo Du, Yun |
| author_facet | Ling, Feng Zhang, Yihang Foody, Giles M. Li, Xiaodong Zhang, Xiuhua Fang, Shiming Li, Wenbo Du, Yun |
| author_sort | Ling, Feng |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Super-resolution mapping (SRM) is a technique for generating a fine spatial resolution land cover map from coarse spatial resolution fraction images estimated by soft classification. The prior model used to describe the fine spatial resolution land cover pattern is a key issue in SRM. Here, a novel learning based SRM algorithm, whose prior model is learned from other available fine spatial resolution land cover maps, is proposed. The approach is based on the assumption that the spatial arrangement of the land cover components for mixed pixel patches with similar fractions is often similar. The proposed SRM algorithm produces a learning database that includes a large number of patch pairs for which there is a fine and coarse spatial resolution representation for the same area. From the learning database, patch pairs that have similar coarse spatial resolution patches as those in input fraction images are selected. Fine spatial resolution patches in these selected patch pairs are then used to estimate the latent fine spatial resolution land cover map, by solving an optimization problem. The approach is illustrated by comparison against state-of-the-art SRM methods using land cover map subsets generated from the USA’s National Land Cover Database. Results show that the proposed SRM algorithm better maintains the spatial pattern of land covers for a range of different landscapes. The proposed SRM algorithm has the highest overall accuracy and Kappa values in all these SRM algorithms, by using the entire maps in the accuracy assessment. |
| first_indexed | 2025-11-14T19:17:37Z |
| format | Article |
| id | nottingham-32958 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:17:37Z |
| publishDate | 2016 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-329582020-05-04T17:52:56Z https://eprints.nottingham.ac.uk/32958/ Learning-based superresolution land cover mapping Ling, Feng Zhang, Yihang Foody, Giles M. Li, Xiaodong Zhang, Xiuhua Fang, Shiming Li, Wenbo Du, Yun Super-resolution mapping (SRM) is a technique for generating a fine spatial resolution land cover map from coarse spatial resolution fraction images estimated by soft classification. The prior model used to describe the fine spatial resolution land cover pattern is a key issue in SRM. Here, a novel learning based SRM algorithm, whose prior model is learned from other available fine spatial resolution land cover maps, is proposed. The approach is based on the assumption that the spatial arrangement of the land cover components for mixed pixel patches with similar fractions is often similar. The proposed SRM algorithm produces a learning database that includes a large number of patch pairs for which there is a fine and coarse spatial resolution representation for the same area. From the learning database, patch pairs that have similar coarse spatial resolution patches as those in input fraction images are selected. Fine spatial resolution patches in these selected patch pairs are then used to estimate the latent fine spatial resolution land cover map, by solving an optimization problem. The approach is illustrated by comparison against state-of-the-art SRM methods using land cover map subsets generated from the USA’s National Land Cover Database. Results show that the proposed SRM algorithm better maintains the spatial pattern of land covers for a range of different landscapes. The proposed SRM algorithm has the highest overall accuracy and Kappa values in all these SRM algorithms, by using the entire maps in the accuracy assessment. Institute of Electrical and Electronics Engineers 2016-05-06 Article PeerReviewed Ling, Feng, Zhang, Yihang, Foody, Giles M., Li, Xiaodong, Zhang, Xiuhua, Fang, Shiming, Li, Wenbo and Du, Yun (2016) Learning-based superresolution land cover mapping. IEEE Transactions on Geoscience and Remote Sensing, 54 (7). pp. 3794-3810. ISSN 0196-2892 Super-resolution mapping; learning database; patch pairs; neighboring patches http://dx.doi.org/10.1109/TGRS.2016.2527841 doi:10.1109/TGRS.2016.2527841 doi:10.1109/TGRS.2016.2527841 |
| spellingShingle | Super-resolution mapping; learning database; patch pairs; neighboring patches Ling, Feng Zhang, Yihang Foody, Giles M. Li, Xiaodong Zhang, Xiuhua Fang, Shiming Li, Wenbo Du, Yun Learning-based superresolution land cover mapping |
| title | Learning-based superresolution land cover mapping |
| title_full | Learning-based superresolution land cover mapping |
| title_fullStr | Learning-based superresolution land cover mapping |
| title_full_unstemmed | Learning-based superresolution land cover mapping |
| title_short | Learning-based superresolution land cover mapping |
| title_sort | learning-based superresolution land cover mapping |
| topic | Super-resolution mapping; learning database; patch pairs; neighboring patches |
| url | https://eprints.nottingham.ac.uk/32958/ https://eprints.nottingham.ac.uk/32958/ https://eprints.nottingham.ac.uk/32958/ |