• Stars
    star
    204
  • Rank 192,063 (Top 4 %)
  • Language
    C++
  • Created over 2 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

[RA-L 2022] Ctrl-VIO: Continuous-Time Visual-Inertial Odometry for Rolling Shutter Cameras

Ctrl-VIO

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

sw-traj-opt

Ctrl-VIO is a highly-accurate continuous-time visual-inertial odometry system with online calibration for the line exposure time difference (line delay) of the rolling shutter cameras , using continuous-time trajectory parameterized by B-splines to elegantly handle the rolling shutter effect, which outperforms SOTA global shutter method VIO and rolling shutter method VIO on rolling shutter data. A novel marginalization strategy for continuous-time framework is proposed and implemented.

The source code will be available after the publication of the related paper.

Evaluation on TUM-RSVI Dataset

YouTube

Ctrl-VIO-TUMRSVI

rmse

The RMSE(m) of APE results of GS methods on GS data, and both GS methods and RS methods on RS data in TUM-RSVI Dataset. The best results are marked in bold and the second best results are marked in blue.