Sub-pixel mapping of remote sensing images based on radial basis function interpolation

Abstract

In this paper, a new sub-pixel mapping (SPM) method based on radial basis function (RBF) interpolation is proposed for land cover mapping at the sub-pixel scale. The proposed method consists of sub-pixel soft class value estimation and subsequent class allocation for each sub-pixel. The sub-pixel soft class values are calculated by RBF interpolation. Taking the coarse proportion images as input, an interpolation model is built for each visited coarse pixel. First, the spatial relations between any sub-pixel within a visited coarse resolution pixel and its surrounding coarse resolution pixels are quantified by the basis function. Second, the coefficients indicating the contributions from neighboring coarse pixels are calculated. Finally, the basis function values are weighted by the coefficients to predict the sub-pixel soft class values. In the class allocation process, according to the class proportions and estimated soft class values, sub-pixels are allocated one of each available class in turn. Three remote sensing images were tested and the new method was compared to bilinear-, bicubic-, sub-pixel/pixel spatial attraction model- and Kriging-based SPM methods. Results show that the proposed RBF interpolation-based SPM is more accurate. Hence the proposed method provides an effective new option for SPM.