Graph-based visual SLAM and visual odometry using an RGB-D camera

Abstract

In this paper we present a real-time graph-based visual SLAM approach. The presented visual SLAM algorithm can be separated into three parts: feature extraction, data association, and SLAM back-end. We use FAST for feature detection and the Binary Robust Independent Elementary Features (BRIEF) as feature descriptor, which together provide a fast and stable feature extraction. The data association is solved using Locality Sensitive Hashing (LSH), which uses local hash tables and profits from binary feature descriptors. As SLAM back-end we use the general graph optimization framework g 2 o, which is designed to provide solutions to several SLAM variants. We further provide a novel approach to visual odometry by combining recent sensor measurements into a small pose graph and optimizing it using g 2 o. For finding potential neighbour nodes and loop closures we introduce the Global Feature Repository (GFR). GFR searches for loop closures and potential neighbours independent of their position in the graph. Finally, we show the accuracy and real-time ability of our algorithm by comparing it to a recently published benchmark dataset. We further provide some large-scale datasets using state-of-the-art laser localization as ground-truth.

Real-Time RGB-D Simultaneous Localization and Mapping Guided by Terrestrial LiDAR Point Cloud for Indoor 3-D Reconstruction and Camera Pose Estimation

“…With lightweight and low-cost RGB-D sensors, such as Microsoft Kinetic, becoming increasingly popular, RGB-D SLAM has attracted significant attention from researchers. For example, a pose graph optimization framework is proposed to realize real-time and highly accurate SLAM [21,22]. In addition, the conventional bundle adjustment framework is extended to incorporate the RGB-D data with inertial measurement unit to optimize mapping and pose estimation in an integrated manner [23][24][25].…”

3D visual SLAM with a Time-of-Flight camera

“…Generally, solutions to SLAM are the use of Kalman Filter (KF), Particle Filter (PF) and Monte Carlo (MC),etc [1][2][3][4], and one of solutions to 3D SLAM is based on the registration of range image, whose key issue is the estimation of perspective or movement.…”