Towards Precise Visual Navigation and Direct Georeferencing for MAV Using ORB-SLAM2

A low accuracy of positioning using Global Navigation Satellite System (GNSS) are not meet geodetic requirements for direct images georeferencing for Unmanned Aerial Vehicle (UAV) photogrammetry. A majority of UAVs are equipped with a monocular or stereo non-metric cameras for either visual data gathering or live video feed for operator. A cheap positioning techniques used on board commercial UAVs are not that precise as geodetic community requires. Moreover, a traditional satellite navigation suffers from a multipath Global Positioning System (GPS) signal in an industrial environment and cities or during operation in poor GPS space segment geometry or in indoor environment. In that cases, the UAV position can be enhanced by a visual navigation method. The paper presents a results of implementation of recently developed robust simultaneous localization and mapping method for a low cost hexacopter platforms navigation system augmentation, in order to support a precise and robust direct images georeferencing.