Extracting urban ground object information from images and LiDAR data

To deal with the problem of urban ground object information extraction, the paper proposes an object-oriented classification method using aerial image and LiDAR data. Firstly, we select the optimal segmentation scales of different ground objects and synthesize them to get accurate object boundaries. Then, we use ReliefF algorithm to select the optimal feature combination and eliminate the Hughes phenomenon. Finally, we use the multiple classifier combination method to get the classification result. To validate the method, we classify two research regions (region A covers around 0.21km2, and region B about 1.1km2) in Stuttgart, Germany. The first experiment on region A is to select the optimal segmentation scales and classification features. The overall accuracy of the classification reaches to 93.3%. The experiment on region B is implemented to validate the application-ability of this method for large area, which achieves 88.42% overall accuracy. It can be concluded that the proposed method improves the accuracy and efficiency of urban ground object information extraction and has a high application value.