A novel land cover mapping algorithm based on random forest and Markov random field models

This paper proposes a new land cover mapping algorithm that combines the strengths of random forest (RF) with a Markov random field (MRF) model. The idea is to transform the observed data into the decision domain of weak classifiers inside an RF. Due to how RF are trained, these decisions can be considered to be independent from each others, and therefore the joint probability density function in the decision domain can be both easily and accurately estimated. For a decision vector from RF, and under an MRF model, the optimum land cover map is iteratively searched. The performances of the proposed algorithm were evaluated using a real remote-sensing image, and we found that the resulting land cover maps are more accurate than most traditional classifiers in all sizes of training samples.