Localization Using Single Camera and Lidar in Gps-Denied Environments

Abstract

Location estimation for ground and air vehicles is mostly realized by fusion of global positioning system (gps / gnss) and data from sensors such as inertial measurement unit, barometer, wheel odometer, etc. However, in case GPS is not available, location estimation is an open problem. Considering the various advantages and disadvantages of all these sensors that can be used for position estimation, it is noticed that there is no single and absolute solution to the problem of three-dimensional, 6 degrees-of-freedom localization. Especially in GPS-denied environments, precise localization methods for ground and air vehicles are still an important research area. While these periods of studies on autonomous vehicles gained speed, the localization problem with camera and lidar has been an alternative research topic which has strengthened its place in the literature. In this study; a new solution is proposed that addresses the problem of 6-DOF localization using a single camera and lidar where gps signal is not available.