Intuitive Terrain Reconstruction Using Height Observation-Based Ground Segmentation and 3D Object Boundary Estimation

Abstract

Mobile robot operators must make rapid decisions based on information about the robot’s surrounding environment. This means that terrain modeling and photorealistic visualization are required for the remote operation of mobile robots. We have produced a voxel map and textured mesh from the 2D and 3D datasets collected by a robot’s array of sensors, but some upper parts of objects are beyond the sensors’ measurements and these parts are missing in the terrain reconstruction result. This result is an incomplete terrain model. To solve this problem, we present a new ground segmentation method to detect non-ground data in the reconstructed voxel map. Our method uses height histograms to estimate the ground height range, and a Gibbs-Markov random field model to refine the segmentation results. To reconstruct a complete terrain model of the 3D environment, we develop a 3D boundary estimation method for non-ground objects. We apply a boundary detection technique to the 2D image, before estimating and refining the actual height values of the non-ground vertices in the reconstructed textured mesh. Our proposed methods were tested in an outdoor environment in which trees and buildings were not completely sensed. Our results show that the time required for ground segmentation is faster than that for data sensing, which is necessary for a real-time approach. In addition, those parts of objects that were not sensed are accurately recovered to retrieve their real-world appearances.

An Interactive Image Segmentation Method in Hand Gesture Recognition

“…The overall color modelling completes the first step in our human visual system, to take every detail of the image into account, Gibbs random field (GRF) [29] is introduced. GRF is defined as: $P(\mathit{A}=\mathit{a})=\frac{1}{Z(T)}\exp (-\frac{1}{T}E(\mathit{\alpha })),$…”

Sloped Terrain Segmentation for Autonomous Drive Using Sparse 3D Point Cloud

“…Song et al carried out ground segmentation using height histograms and a Gibbs-Markov random field model to reconstruct the geography into a 3D model [ 10 ]. However, the efficiency of its algorithm for slopes has not been verified.…”

Real-Time Terrain Storage Generation from Multiple Sensors towards Mobile Robot Operation Interface

“…In this study, we propose the use of a voxel map to represent nonground objects and a terrain mesh to represent the ground surface. Therefore, we classify these points into ground and nonground using the height histogram method [ 11 ] before terrain modeling.…”

“…To register the sensed datasets into the terrain model having limited memory, we develop a voxel-based flag map as a comparative table for removing redundant points. The compressed point clouds are registered into a nonground point database (PDB) and ground texture database (MDB) using a height histogram method [ 11 ]. To visualize the reconstructed terrain model, the nonground PDB is represented using a voxel map, generated by integrating the nonground 3D points into regular grids.…”