3D Scene Reconstruction Using Omnidirectional Vision and LiDAR: A Hybrid Approach

Abstract

In this paper, we propose a novel approach to obtain accurate 3D reconstructions of large-scale environments by means of a mobile acquisition platform. The system incorporates a Velodyne LiDAR scanner, as well as a Point Grey Ladybug panoramic camera system. It was designed with genericity in mind, and hence, it does not make any assumption about the scene or about the sensor set-up. The main novelty of this work is that the proposed LiDAR mapping approach deals explicitly with the inhomogeneous density of point clouds produced by LiDAR scanners. To this end, we keep track of a global 3D map of the environment, which is continuously improved and refined by means of a surface reconstruction technique. Moreover, we perform surface analysis on consecutive generated point clouds in order to assure a perfect alignment with the global 3D map. In order to cope with drift, the system incorporates loop closure by determining the pose error and propagating it back in the pose graph. Our algorithm was exhaustively tested on data captured at a conference building, a university campus and an industrial site of a chemical company. Experiments demonstrate that it is capable of generating highly accurate 3D maps in very challenging environments. We can state that the average distance of corresponding point pairs between the ground truth and estimated point cloud approximates one centimeter for an area covering approximately 4000 m2. To prove the genericity of the system, it was tested on the well-known Kitti vision benchmark. The results show that our approach competes with state of the art methods without making any additional assumptions.

Analysis of 3D Scan Measurement Distribution with Application to a Multi-Beam Lidar on a Rotating Platform

“…Furthermore, the increased vertical resolution of the HDL-32 has a significant impact in the cost of the sensor, which is substantially more expensive than the VLP-16. These features have favored the adoption of MBLs in mobile applications, where dynamic point cloud registration along the vehicle’s path compensates for device limitations in vertical resolution and FOV [ 34 ]. Nevertheless, MBLs have to be rotated to yield a complete spherical FOV [ 12 ].…”

Have I Seen This Place Before? A Fast and Robust Loop Detection and Correction Method for 3D Lidar SLAM

“…The loop closure method developed in this work is part of an entire 3D mapping system that was presented in [24] and [25]. As in that work, we use lidar data originating from Velodyne scanners, including the VLP-16, HDL-32E, and HDL-64E.…”

“…As in that work, we use lidar data originating from Velodyne scanners, including the VLP-16, HDL-32E, and HDL-64E. One of the main contributions of [24] was a scan matching framework that aligns newly acquired point clouds with an online built 3D map. As stated in the introduction, this procedure is prone to error accumulation, and for that reason we improve it by actively detecting loops, i.e., locations that the robot or mobile platform is visiting more than once, in order to propagate the error back in the SLAM pose graph.…”

High Definition 3D Map Creation Using GNSS/IMU/LiDAR Sensor Integration to Support Autonomous Vehicle Navigation

“…The matching time of the NDT is better than ICP because NDT does not require point-to-point registration [34]. However, the determination of the grid size is a critical step in this algorithm, which is an issue for inhomogeneous point clouds [41] that dominate the estimation stability and determines the performance of the algorithm [35]. This algorithm has been used for many applications, such as path planning, change detection, and loop detection [32].…”