search

url-kaist / kaistviodataset

"Visual-Inertial Dataset" (RA-L'21 with ICRA'21): it contains harsh motions for VO/VIO, like pure rotation or fast rotation with various motion types.
GNU General Public License v3.0
75 stars 7 forks source link
visual-inertial-odometry visual-odometry

readme

KAIST VIO dataset (RA-L'21 w/ ICRA Option)

Official page of "Run Your Visual-Inertial Odometry on NVIDIA Jetson: Benchmark Tests on a Micro Aerial Vehicle", which is accepted by RA-L with ICRA'21 option

[![video](https://img.shields.io/badge/YouTube-B31B1B.svg)](https://www.youtube.com/watch?v=nZzgyhNimLI) [![arxiv](https://img.shields.io/badge/arXiv-2103.01655-B31B1B.svg)](https://arxiv.org/abs/2103.01655) [![journal](https://img.shields.io/badge/paper-RA_L%202021-4b44ce.svg)](https://ieeexplore.ieee.org/abstract/document/9416140)

This is the dataset for testing the robustness of various VO/VIO methods, acquired on a UAV.

You can download the whole dataset on KAIST VIO dataset


# Contents 1. [Trajectories](#Trajectories) 2. [Downloads](#Downloads) 3. [Dataset format](#Dataset-format) 4. [Setup](#Setup) 5. [Citation](#Citation)

## Trajectories


+ Four different trajectories: + *circle* + *infinity* + *square* + *pure_rotation* + Each trajectory has three types of sequence: + *normal speed* + *fast speed* + *rotation* + The *pure rotation* sequence has only *normal speed, fast speed* types

## Downloads You can download a single ROS bag file from the link below. (or whole dataset from [KAIST VIO dataset](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/kaist_vio_dataset.zip))
| Trajectory | Type | ROS bag download | | :---: | :--- | :---: | | **circle** | normal
fast
rotation | [link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle_fast.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle_head.bag) | | **infinity** | normal
fast
rotation | [link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite_fast.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite_head.bag) | | **square** | normal
fast
rotation | [link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square_fast.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square_head.bag) | | **rotation** | normal
fast | [link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/rotation/rotation.bag)
[link](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/rotation/rotation_fast.bag) |>

## Dataset format


+ Each set of data is recorded as a **ROS bag** file. + Each **data** sequence contains the followings: + stereo infra images (w/ emitter turned off) + mono RGB image + IMU data (3-axes accelerometer, 3-axes gyroscopes) + 6-DOF Ground-Truth + ROS topic + Camera(30 Hz): *"/camera/infra1(2)/image_rect_raw/compressed", "/camera/color/image_raw/compressed"* + IMU(100 Hz): *"/mavros/imu/data"* + Ground-Truth(50 Hz): *"/pose_transformed"* + In the **config** directory + trans-mat.yaml: translational matrix between the origin of the Ground-Truth and the VI sensor unit.
(the offset has already been applied to the bag data, and this YAML file has estimated offset values, just for reference. To benchmark your VO/VIO method more accurately, you can use your alignment method with other tools, like origin alignment or Umeyama alignment from [evo](https://github.com/MichaelGrupp/evo)) + imu-params.yaml: estimated noise parameters of Pixhawk 4 mini + cam-imu.yaml: Camera intrinsics, Camera-IMU extrinsics in kalibr format - publish ground truth as trajectory ROS topic - ground truth are recorded as 'geometry_msgs/PoseStamped' - but you may want to acquire 'nav_msgs/Path' rather than just 'Pose' for visuaslization purpose (e.g. Rviz) - For this, you can refer this package for 'geometry_msgs/PoseStamped'->'nav_msgs/Path': [tf_to_trajectory](https://github.com/engcang/tf_to_trajectory#execution)

## Setup #### - Hardware


                                                            Fig.1 Lab Environment                                        Fig.2 UAV platform
+ **VI sensor unit** + camera: Intel Realsense D435i (640x480 for infra 1,2 & RGB images) + IMU: Pixhawk 4 mini + VI sensor unit was calibrated by using [kalibr](https://github.com/ethz-asl/kalibr)
+ **Ground-Truth** + OptiTrack PrimeX 13 motion capture system with six cameras was used + including 6-DOF motion information.

#### - Software (VO/VIO Algorithms): How to set each (publicly available) algorithm on the jetson board | VO/VIO | Setup link | | :---: | :---: | | **VINS-Mono** | [link](https://github.com/zinuok/VINS-MONO) | | **ROVIO** | [link](https://github.com/zinuok/Rovio) | | **VINS-Fusion** | [link](https://github.com/zinuok/VINS-Fusion) | | **Stereo-MSCKF** | [link](https://github.com/zinuok/MSCKF_VIO) | | **Kimera** | [link](https://github.com/zinuok/Kimera-VIO-ROS) | ## Citation If you use the algorithm in an academic context, please cite the following publication: ``` @article{jeon2021run, title={Run your visual-inertial odometry on NVIDIA Jetson: Benchmark tests on a micro aerial vehicle}, author={Jeon, Jinwoo and Jung, Sungwook and Lee, Eungchang and Choi, Duckyu and Myung, Hyun}, journal={IEEE Robotics and Automation Letters}, volume={6}, number={3}, pages={5332--5339}, year={2021}, publisher={IEEE} } ``` ## Lisence This datasets are released under the Creative Commons license (CC BY-NC-SA 3.0), which is free for non-commercial use (including research).
  • © Githubissues.
  • Githubissues is a development platform for aggregating issues.