AUTOMATED EXTRACTION OF BUILDINGS FROM AERIAL LIDAR POINT CLOUDS AND DIGITAL IMAGING DATASETS
To acquire 3D geospatial information, LiDAR technology provides the rapid, continuous and cost-effective capability. In this paper, two automated approaches for extracting building features from the integrated aerial LiDAR point cloud and digital imaging datasets are proposed. The assumption of the two approaches is that the LiDAR data can be used to distinguish between high- and low-rise objects while the multispectral dataset can be used to filter out vegetation from the data. Object-based image analysis techniques are applied to the extracted building objects. The two automated buildings extraction approaches are tested on a fusion of aerial LiDAR point cloud and digital imaging datasets of Istanbul city. The object-based automated technique presents better results compared to the threshold-based technique for extraction of building objects in term of visual interpretation.