FastTrack: GPU-Accelerated Tracking for Visual SLAM
For SLAM researchers and practitioners, this work offers a practical acceleration of a known bottleneck in visual-inertial SLAM tracking.
The authors present a GPU-accelerated approach for the tracking module of visual-inertial SLAM, achieving up to 2.8x speedup on desktop and Jetson Xavier NX using ORB-SLAM3 on EuRoC and TUM-VI datasets.
The tracking module of a visual-inertial SLAM system processes incoming image frames and IMU data to estimate the position of the frame in relation to the map. It is important for the tracking to complete in a timely manner for each frame to avoid poor localization or tracking loss. We therefore present a new approach which leverages GPU computing power to accelerate time-consuming components of tracking in order to improve its performance. These components include stereo feature matching and local map tracking. We implement our design inside the ORB-SLAM3 tracking process using CUDA. Our evaluation demonstrates an overall improvement in tracking performance of up to 2.8x on a desktop and Jetson Xavier NX board in stereo-inertial mode, using the well-known SLAM datasets EuRoC and TUM-VI.