Progress and perspectives of point cloud intelligence

With the rapid development of reality capture methods, such as laser scanning and oblique photogrammetry, point cloud data have become third most important source, after vector maps imagery. Point also play an increasingly role in scientific research engineering fields Earth science, spatial cognition, smart cities. However, how to acquire high-quality three-dimensional (3D) geospatial information from clouds has a frontier, for which there is urgent demand surveying mapping, well geoscience applications. To address challenges mentioned above, intelligence came into being. This paper summarizes state-of-the-art intelligence, with regard acquisition equipment, intelligent processing, research, For this purpose, we refer recent project on hybrid georeferencing images LiDAR collection, current benchmark semantic segmentation high-resolution 3D clouds. These projects were conducted at Institute Photogrammetry, University Stuttgart, was initially headed by late Prof. Ackermann. Finally, prospects are summarized.