Please use this identifier to cite or link to this item:
|Title:||3D scene reconstruction Based on a 2D moving LiDAR|
|Authors:||Murcia Moreno, Harold Fabián|
Monroy, Maria Fernanda
Mora, Luis Fernando
3D point clouds
|Citation:||Murcia H.F., Monroy M.F., Mora L.F. (2018) 3D Scene Reconstruction Based on a 2D Moving LiDAR. In: Florez H., Diaz C., Chavarriaga J. (eds) Applied Informatics. ICAI 2018. Communications in Computer and Information Science, vol 942. Springer, Cham|
|Abstract:||A real-world reconstruction from a computer graphics tool is one of the main issues in two different communities: robotics and artificial intelligence, both of them under different points of view such as computer science, perception and machine vision. A real scene can be reconstructed by generating of point clouds with the help of depth sensors, rotational elements and mathematical transformations according to the mechanical design. This paper presents the development of a three-dimensional laser range finder based on a two-dimensional laser scanner Hokuyo URG-04LX-UG01 and a step motor. The design and kinematic model of the system to generate 3D point clouds are presented with an experimental acquisition algorithm implemented on Robotic Operative System ROS in Python language. The quality of the generated reconstruction is improved with a calibration algorithm based on a model parameter optimization from a reference surface, the results from the calibrated model were compared with a commercial low-cost device. The concurrent application of the system permits the viewing of the scene from different perspectives. The output files can be easily visualized with Python or MATLAB and used for surface reconstruction, scene classification or mapping. In this way, typical robotic tasks can be realized, highlighting autonomous navigation, collision avoidance, grasp calculation and handling of objects.|
|Appears in Collections:||Artículos|
Files in This Item:
There are no files associated with this item.
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.