Soft-then-hard sub-pixel mapping with multiple shifted images

Abstract

The soft-then-hard sub-pixel mapping (STHSPM) algorithm is a type of sub-pixel mapping (SPM) algorithm that first estimates the soft class values for sub-pixels at the target fine spatial resolution and then predicts the hard class labels for sub-pixels. In this article, four fast STHSPM algorithms (i.e. bilinear, bicubic, kriging, and radial basis function interpolation) were enhanced by using multiple shifted images (MSIs). The proportion images of the MSIs were first downscaled to the desired fine spatial resolution and then the multiple downscaled images were integrated for each class, followed by the class allocation process. Three remote-sensing images were used to test the proposed methods, and the results showed that MSIs can help to increase the SPM accuracy of the four STHSPM algorithms. The approach to incorporating MSIs into the STHSPM algorithms is non-iterative and fast.

Acknowledgements

The authors would like to thank Dr Andrew J. Tatem of the University of Southampton for providing the aerial image and its land-cover map, Prof. Gamba of the University of Pavia for providing the ROSIS data, and Dr Lefei Zhang of Wuhan University for providing the land-cover map of the ROSIS data. They would also like to thank the anonymous reviewers whose valuable and constructive comments have greatly improved this article.

Additional information

Funding

This work was supported by the Research Grants Council of Hong Kong under Grant PolyU 5249/12E, the Ministry of Science and Technology of China under Project 2012BAJ15B04 and Project 2012AA12A305, and by the National Natural Science Foundation of China under Grants 41331175 and 41201451.