Ctrl-VIO: Continuous-Time Visual-Inertial Odometry for Rolling Shutter Cameras
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.
-
ROS (tested with Melodic)
-
Eigen3
-
Ceres 1.14
-
OpenCV 3.3
-
yaml-cpp
sudo apt-get install libyaml-cpp-dev
mkdir -p ~/catkin_ctrlvio/src
cd ~/catkin_ctrlvio/src
git clone https://github.com/APRIL-ZJU/Ctrl-VIO.git
cd ~/catkin_ctrlvio
catkin_make
source devel/setup.bash
-
Download TUM-RSVI Dataset.
-
Configure parameters in the
config/ct_odometry_tumrs.yaml
file.log_path
: the path to logconfig_path
: the path ofconfig
folderbag_path
: the file path of rosbag
-
Run on TUM-RSVI Dataset for example.
roslaunch ctrlvio odometry.launch
This code was developed by Xiaolei Lang and Jiajun Lv from APRIL Lab in Zhejiang University.
For researchers that have leveraged or compared to this work, please cite the following:
@article{lang2022ctrl,
title={Ctrl-vio: Continuous-time visual-inertial odometry for rolling shutter cameras},
author={Lang, Xiaolei and Lv, Jiajun and Huang, Jianxin and Ma, Yukai and Liu, Yong and Zuo, Xingxing},
journal={IEEE Robotics and Automation Letters},
volume={7},
number={4},
pages={11537--11544},
year={2022},
publisher={IEEE}
}
Thanks for their excellent job!
The code is released under the GNU General Public License v3 (GPL-3).