To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding. In this paper, a 3D surface reconstruction algorithm from heterogeneous density 3D data is presented. The proposed method is based on a TSDF voxel-based representation, where an adaptive neighborhood kernel sourced on a Gaussian confidence evaluation is introduced. This enables to keep a good trade-off between the density of the reconstructed mesh and its accuracy. Experimental evaluations carried on both synthetic (CARLA) and real (KITTI) 3D data show a good performance compared to a state of the art method used for surface reconstruction.
3D Surface Reconstruction from Voxel-based Lidar Data
2019-10-01
3050986 byte
Conference paper
Electronic Resource
English
Photorealistic Scene Reconstruction by Voxel Coloring
British Library Online Contents | 1999
|Transportation Research Record | 2018
|