Hybrid elevation maps: 3D surface models for segmentation

This paper presents an algorithm for segmenting 3D point clouds. It extends terrain elevation models by incorporating two types of representations: (1) ground representations based on averaging the height in the point cloud, (2) object models based on a voxelisation of the point cloud. The approach is deployed on Riegl data (dense 3D laser data) acquired in a campus type of environment and compared against six other terrain models. Amongst elevation models, it is shown to provide the best fit to the data as well as being unique in the sense that it jointly performs ground extraction, overhang representation and 3D segmentation. We experimentally demonstrate that the resulting model is also applicable to path planning.

Authors

• Bertrand Douillard
• James Patrick Underwood
• Narek Melkumyan
• Surya P. N. Singh
• Shrihari Vasudevan
• Christopher Joseph Brunner
• Alastair James Quadros

Keywords

• Three dimensional displays
• Computational modeling
• Laser modes
• Noise measurement
• Clouds
• Buildings
• Context
• Topographic Maps
• Point Cloud
• Path Planning
• 3D Point Cloud
• Terrain Model
• 3D Segmentation
• Root Mean Square Error
• Mean Square Error
• Computation Time
• Body Height
• Flat Surface
• Grid Cells
• Segmentation Algorithm
• Ground Surface
• Tree Canopy
• Vertical Bars
• Object Segmentation
• Palm Trees
• Hybrid Algorithm
• Meaning Maps
• Ground Model
• Least Square Error
• Point Cloud Segmentation
• Ground Height