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

TL;DR

This paper introduces Ctrl-VIO, a probabilistic continuous-time visual-inertial odometry system tailored for rolling shutter cameras, effectively handling asynchronous sensor data and motion distortion with online calibration.

Contribution

It presents a novel continuous-time VIO framework that incorporates probabilistic marginalization and online calibration for rolling shutter cameras, improving accuracy and efficiency.

Findings

Outperforms existing state-of-the-art VIO methods on multiple datasets.

Effectively handles motion distortion in rolling shutter images.

Enables online calibration of line delay in the VIO system.

Abstract

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