In this paper we propose a joint approach on virtual city reconstruction and dynamic scene analysis based on point cloud sequences of a single car-mounted Rotating Multi-Beam (RMB) Lidar sensor. The aim of the addressed work is to create 4D spatio-temporal models of large dynamic urban scenes containing various moving and static objects. Standalone RMB Lidar devices have been frequently applied in robot navigation tasks and proved to be efficient in moving object detection and recognition. However, they have not been widely exploited yet for geometric approximation of ground surfaces and building facades due to the sparseness and inhomogeneous density of the individual point cloud scans. In our approach we propose an automatic registration method of the consecutive scans without any additional sensor information such as IMU, and introduce a process for simultaneously extracting reconstructed surfaces, motion information and objects from the registered dense point cloud completed with point time stamp information.
Automatic reconstruction of large-scale outdoor objects like house facades is an important component of mixedreality systems that model and visualise real world at different level of detail. The authors are involved in a project that utilises a car-mounted LIDAR to acquire a sequence 3D point clouds representing facades in a street. No GPS or IMU is used. Hundreds of point clouds need to be automatically aligned to obtain a realistic surface model of facades. In this paper, we present and compare two solutions to this complex registration problem. Our methods are based on two different, widely used techniques for registering two partially overlapping point clouds in presence of outliers. The proposed algorithms are capable of automatically detecting occasional misalignments. We analyse the operation of the algorithms paying special attention to the robustness, speed and optimal parameter setting.
Abstract-In this paper, we introduce a system framework which can automatically interpret large point cloud datasets collected from dense urban areas by moving aerial or terrestrial Lidar platforms. We propose novel algorithms for region segmentation, motion analysis, object identification and population level scene analysis which steps can highly contribute to organize the data into a semantically indexed structure, enabling quick responses for content based user queries about the environment. The system is tested on real Lidar data, and for demonstration quantitative evaluation is given on vehicle detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.