An iterative interpolation deconvolution algorithm for superresolution land cover mapping

Ling, Feng; Foody, Giles M.; Ge, Yong; Li, Xiaodong; Du, Yun

Abstract

Super-resolution mapping (SRM) is a method to produce a fine spatial resolution land cover map from coarse spatial resolution remotely sensed imagery. A popular approach for SRM is a two-step algorithm, which first increases the spatial resolution of coarse fraction images by interpolation, and then determines class labels of fine resolution pixels using the maximum a posteriori (MAP) principle. By constructing a new image formation process that establishes the relationship between observed coarse resolution fraction images and the latent fine resolution land cover map, it is found that the MAP principle only matches with area-to-point interpolation algorithms, and should be replaced by de-convolution if an area-to-area interpolation algorithm is to be applied. A novel iterative interpolation de-convolution (IID) SRM algorithm is proposed. The IID algorithm first interpolates coarse resolution fraction images with an area-to-area interpolation algorithm, and produces an initial fine resolution land cover map by de-convolution. The fine spatial resolution land cover map is then updated by re-convolution, back-projection and de-convolution iteratively until the final result is produced. The IID algorithm was evaluated with simulated shapes, simulated multi-spectral images, and degraded Landsat images, including comparison against three widely used SRM algorithms: pixel swapping, bilinear interpolation, and Hopfield neural network. Results show that the IID algorithm can reduce the impact of fraction errors, and can preserve the patch continuity and the patch boundary smoothness, simultaneously. Moreover, the IID algorithm produced fine resolution land cover maps with higher accuracies than those produced by other SRM algorithms.

Citation

Ling, F., Foody, G. M., Ge, Y., Li, X., & Du, Y. (2016). An iterative interpolation deconvolution algorithm for superresolution land cover mapping. IEEE Transactions on Geoscience and Remote Sensing, 54(12), 7210-7222. https://doi.org/10.1109/TGRS.2016.2598534

• Journal Article Type: Article
• Acceptance Date: Aug 2, 2016
• Online Publication Date: Aug 26, 2016
• Publication Date: Dec 31, 2016
• Deposit Date: Oct 26, 2016
• Publicly Available Date: Oct 26, 2016
• Journal: IEEE Transactions on Geoscience and Remote Sensing
• Print ISSN: 0196-2892
• Electronic ISSN: 1558-0644
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 54
• Issue: 12
• Pages: 7210-7222
• DOI: https://doi.org/10.1109/TGRS.2016.2598534
• Keywords: Interpolation, De-convolution, Super-resolution Mapping
• Public URL: https://nottingham-repository.worktribe.com/output/831344
• Publisher URL: http://ieeexplore.ieee.org/document/7553472/
• Additional Information: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
• Contract Date: Oct 26, 2016