Land cover mapping at sub-pixel scales using remote sensing imagery

One of the great challenges of land cover mapping from remotely sensed images is the mixed pixel problem. Much research has focused on attempting to extract land cover types at sub-pixel scale, while little research has been conducted concerning the spatial allocation of land cover types within a pixel. The "pixel-swapping" optimization algorithm was examined for predicting land cover distribution using remote sensory imagery at a sub-pixel level. Optimum parameters were derived through the experiment.