-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Bag format
All applications in Kalibr use ROS bags as a source for the image and IMU data.
Kalibr requires ROS1 bags, thus you need to convert your bags. You can follow the ROS2 Calibration Using Kalibr guide or convert through the static files using the below bagcreater.
A bagcreater script is provided to use image files and/or IMU data for the calibration
This script allows you to create a ROS bag from raw image files and optionally IMU data. The files have to be organized in folders as illustrated below. The example uses a system with two cameras and one IMU:
+-- dataset-dir
+-- cam0
│ +-- 1385030208726607500.png
│ +-- ...
│ \-- 1385030212176607500.png
+-- cam1
│ +-- 1385030208726607500.png
│ +-- ...
│ \-- 1385030212176607500.png
\-- imu0.csv
The imu0.csv file uses the format below: (timestamps=[ns], omega=[rad/s], alpha=[m/s^2])
timestamp,omega_x,omega_y,omega_z,alpha_x,alpha_y,alpha_z
1385030208736607488,0.5,-0.2,-0.1,8.1,-1.9,-3.3
...
1386030208736607488,0.5,-0.1,-0.1,8.1,-1.9,-3.3
To create the ROS bag run the following command:
kalibr_bagcreater --folder dataset-dir/. --output-bag awsome.bag
In the example above the data would be written to the following topics:
- /cam0/image_raw
- /cam1/image_raw
- /imu0
The bagextractor exports a ROS bag containing image and/or IMU data to image files and an IMU CSV file.
Example usage:
kalibr_bagextractor --image-topics /cam0/image_raw /cam1/image_raw --imu-topics /imu0 --output-folder dataset-dir --bag awsome.bag
NOTE: If you are using the Docker container the output-folder should be relative to the /data
volume directory which is mounted of launch of the container.
Multiple camera calibration
Camera-IMU calibration
Multi-IMU and IMU intrinsic calibration
Rolling Shutter camera calibration
(only ROS):
Camera focus
Calibration validator
ROS2 support
Supported camera models
Calibration targets
Bag format
YAML formats
IMU Noise Model
Example: Calibrating a VI-Sensor
Example: Calibrating RealSense Cameras