Self-Localization of Mobile Robots Using a Single Catadioptric Camera with Line Feature Extraction

Abstract

This paper presents a novel self-localization technique for mobile robots using a central catadioptric camera. A unified sphere model for the image projection is derived by the catadioptric camera calibration. The geometric property of the camera projection model is utilized to obtain the intersections of the vertical lines and ground plane in the scene. Different from the conventional stereo vision techniques, the feature points are projected onto a known planar surface, and the plane equation is used for depth computation. The 3D coordinates of the base points on the ground are calculated using the consecutive image frames. The derivation of motion trajectory is then carried out based on the computation of rotation and translation between the robot positions. We develop an algorithm for feature correspondence matching based on the invariability of the structure in the 3D space. The experimental results obtained using the real scene images have demonstrated the feasibility of the proposed method for mobile robot localization applications.

Quadrotor with wheels: design and experimental evaluation

“…The ORBSLAM2 algorithm 37 is employed to provide a precise location at every point of the quadrotor trajectory. It was chosen because it does not require additional infrastructure, such as other available solutions: OptiTrack 38 , camera tracking 39 , radio frequency (RF) 40 , and terrestrial and satellite semantics tracking 41 . Moreover, the system works in real-time on a RPI in a wide variety of environments such as a laboratory.…”

InertialNet: Inertial Measurement Learning for Simultaneous Localization and Mapping

“…Recently, due to the availability of low-cost sensing devices and the advances of visual-information-processing algorithms, computer vision and machine learning approaches have been used for the development of self-localization and 3D model reconstruction techniques [ 3 ]. A number of SLAM algorithms are applied to commercial applications, which means that mobile robots have the ability of autonomous navigation in structured environments such as offices and factories [ 4 , 5 ]. It is also a current research trend to adopt 3D optical sensors based on dynamic triangulation for the SLAM of a robotic swarm [ 6 ].…”

Calibration of a Catadioptric System and 3D Reconstruction Based on Surface Structured Light

“…The calibration of the intrinsic and extrinsic parameters of the system is an important step in 3D reconstruction. There is much research on the individual calibration of catadioptric cameras, such as Lin H et al [ 14 ], who used the unified sphere model to calibrate a single-viewpoint catadioptric camera, and Guo X et al [ 15 ], who used the Taylor polynomial model to calibrate the catadioptric camera. The active Vision Research Group of Oxford University released the widely used calibration toolbox [ 16 ] for the calibration of catadioptric cameras.…”