Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution swapping

Mapping rural land cover features, such as trees and hedgerows, for ecological applications is a desirable component of the creation of cartographic maps by the Ordnance Survey. Based on the phenomenon of spatial dependence, sub-pixel mapping can provide increased mapping accuracy of such features. A simple pixel-swapping algorithm for sub-pixel mapping was applied to soft classified fine spatial resolution remotely sensed imagery. Initially, Quickbird (TM) satellite sensor imagery with a spatial resolution of 2.6m was acquired of the Christchurch area of Dorset, UK, and three field sites chosen. The imagery was soft classified using a supervised fuzzy c-means algorithm and then super-resolved into sub-pixels using a zoom factor of five. Sub-pixels within pixels were then iteratively swapped until the spatial correlation between sub-pixels for the entire image was maximized. Mathematical morphology was used to suppress error in the super-resolved output, increasing overall accuracy. Field data, including detailed information on the features apparent in the field sites, were used to assess the accuracy of the resultant image. Overall RMSE was between 20 and 30%, resulting in the sub-pixel mapping method producing reasonably accurate results overall of between 50 and 75%. Visual inspection of the super-resolved output shows that the prediction of the position and dimensions of hedgerows was comparable with the original imagery.