A single camera 360‐degree real time vision‐based localization method with application to mobile robot trajectory tracking

Abstract

A method is proposed for real-time vision-based localization in the 360°area around a three-dimensional (3D) reference object with a single camera. The problem is split into three subproblems. First, 360°3D object recognition is proposed, in which a computer vision solution can recognize a reference object from all possible 360°locations. Second, 360°pose estimation is presented, in which the pose of a robot at all locations is estimated. Third, a 360°localization application is integrated with a closed-loop real-time trajectory tracking controller. The successful results of simulations and real experiments of trajectory tracking are also presented.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Drift‐free localisation using prior cross‐source map for indoor low‐light environments

“…Recently, the visual camera used for localisation in the prior map can also get the same excellent results through the efforts of researchers. Although a visual camera has the advantages of small size, lightweight, and low-cost [6], it cannot obtain accurate and reliable localisation results in low-light environments due to its passive perception mechanism. Different from visual cameras, the depth cameras can effectively solve the problem of poor lighting.…”