A random forest based method for urban object classification using lidar data and aerial imagery

Urban land cover classification has always been crucial due to its ability to link many elements of human and physical environments. In this paper, random forest is explored for urban areas. Lidar data and aerial imagery with 0.5-m resolution were used to classify four land categories in the study area located in the City of Niagara Falls (ON, Canada). Based on the experiment results, RF based classification is suited for reducing the data dimensionality of complex urban land cover types in the study area meanwhile reserving discrimination of different classes.