SupSLAM: A Robust Visual Inertial SLAM System Using SuperPoint for Unmanned Aerial Vehicles

Simultaneous localization and mapping (SLAM) is essential for unmanned aerial vehicle (UAV) applications since it allows the UAV to estimate not only its position and orientation but also the map of its working environment. We propose in this study a new SLAM system for UAVs named SupSLAM that works with a stereo camera and an inertial measurement unit (IMU). The system includes a front-end that provides an initial estimate of the UAV position and working environment and a back-end that compensates for the drift caused by the initial estimation. To improve the accuracy and robustness of the system, we use a new feature extraction method named SuperPoint, which includes a pretrained deep neural network to detect key points for estimation. This method is not only accurate in feature extraction but also efficient in computation so that it is relevant to implement on UAVs. We have conducted a number of experiments and comparisons to evaluate the performance of the proposed system. The results show that the system is feasible for UAV SLAM with the performance comparable to state-of-art methods in most datasets and better in some challenging conditions.