作者: Csaba Benedek , Zsolt Jankó , Csaba Horváth , Dömötör Molnár , Dmitry Chetverikov
DOI: 10.1007/978-3-642-39402-7_3
关键词: Computer graphics (images) 、 Trajectory 、 Visualization 、 Point cloud 、 Artificial intelligence 、 Fixed position 、 Computer vision 、 Data type 、 3d model 、 Track (disk drive) 、 Lidar 、 Computer science
摘要: This paper reports on a pilot system for reconstruction and visualisation of complex spatio-temporal scenes by integrating two different types data: outdoor 4D data measured rotating multi-beam LIDAR sensor, models moving actors obtained in studio. A typical scenario is an scene with multiple walking pedestrians. The monitors the from fixed position provides dynamic point cloud. information processed to build 3D model environment detect track Each them represented cluster trajectory. then substituted detailed created output geometrically reconstructed textured avatars that follow real time trajectories