Ctrl-VIO: Continuous-Time Visual-Inertial Odometry for Rolling Shutter Cameras

In this letter, we propose a probabilistic continuous-time visual-inertial odometry (VIO) for rolling shutter cameras. The trajectory formulation naturally facilitates the fusion of asynchronized high-frequency IMU data and motion-distorted images. To prevent intractable computation load, proposed VIO is sliding-window keyframe-based. We to probabilistically marginalize control points keep constant number keyframes in sliding window. Furthermore, line exposure time difference (line delay) camera can be online calibrated our VIO. extensively examine performance VIO, experiments are conducted on publicly-available WHU-RSVI, TUM-RSVI, SenseTime-RSVI datasets. results demonstrate significantly outperforms existing state-of-the-art methods.