Skip to end of metadata
Go to start of metadata

The Kagaru Airborne Dataset is a vision dataset gathered from a radio-controlled aircraft flown at Kagaru, Queensland, Australia on 31/08/10. The data consists of visual data from a pair of downward facing cameras, translation and orientation information as a ground truth from an XSens Mti-g INS/GPS and additional information from a USB NMEA GPS. The dataset traverses over farmland and includes views of grass, an air-strip, roads, trees, ponds, parked aircraft and buildings.

This dataset has been released for free and public use in testing and evaluating stereo visual odometry and visual SLAM algorithms.

A map of the traversed path

The aircraft used for experiments

Sensor layout and coordinate system

An example de-bayered and undistorted stereo pair

YouTube video showing the trajectory

A 3D reconstruction from the data

A 3D reconstruction from the data


If you use this dataset in your own work we request that you cite our paper Large Scale Monocular Vision-only Mapping from a Fixed-Wing sUAS Bib,Ris,XML (EndNote) in your bibliography.

@inproceedings{Warren2012,
address = {Matsushima, Japan},
author = {Warren, Michael and McKinnon, David and He, Hu and Glover, Arren and Shiel, Michael and Upcroft, Ben},
booktitle = {International Conference on Field and Service Robotics},
keywords = {Stereo vision,computer vision,dataset,field robotics,visual odometry,uav,suas},
mendeley-tags = {computer vision,field robotics,visual odometry,uav,suas},
title = {{Large Scale Monocular Vision-only Mapping from a Fixed-Wing sUAS}},
year = {2012}
}




Lost? Follow the Getting Started guide below...

Dataset

Dataset has moved to: http://asrl.utias.utoronto.ca/~mdw/kagarudataset.html

Links are provided to the images and other logs below. The full set of images is available as separated ~1.95GB RAR files, but because of its size a smaller subset of 100 images in both raw and debayered/undistorted formats is also available for evaluation. MD5 Checksums are provided on large files to ensure integrity of downloaded data.

Dataset Title

Master Log Data

Stereo Image Data

Camera Log Data

XSens Log Data

NMEA GPS Log Data

Full Kagaru Airborne Dataset

100 Frame Subset (Frames 2700 to 2800)

See full dataset log

See full dataset log

See full dataset log

See full dataset log

For information on interpreting the log file formats see Log File Formats below.

Sensor/Dataset Details

Sensor

Stereo Vision Rig

XSens Mti-g

USB NMEA GPS

Details

  • Cameras: 2x Pt Grey Flea2 firewire cameras
  • Downward Facing, lengthwise in the fuselage
  • Baseline: ~750mm
  • Resolution: 1280x960 (both cameras)
  • Fujinon 6mm focal length lenses
  • Image Format: BayerGR8 (both cameras)
  • GPS Based latitude, longitude and altitude
  • IMU/Magnetometer/GPS filtered latitude, longitude and altitude
  • Raw IMU and magnetometer data
  • GPS Based latitude, longitude and altitude

Update Frequency

30 fps (125uS resolution)

120 Hz

1 Hz

Number of Logged Items

10396

43578

365

Position and Orientation Information

For ease of transformations, the body co-ordinate system origin is set at the centre of the XSens Mti-g. These locations are accurate to within approximately 10mm. Defined position of GPS antennas is in the centre of the sensor. See the configuration image for clarification. The orientation of the cameras is such that the Z direction is co-incident with the optical axis of the camera.

Sensor

Front Camera

Rear Camera

XSens Mti-g

Xsens GPS

NMEA GPS

Position,t (x,y,z) (m)

0.0, -0.1, -0.05

0.0, 0.7, 0.05

0.0, 0.0, 0.0

0.0, 0.0, 0.11

0.0, -0.1, 0.1

Orientation,r (alpha,beta,gamma) (radians)

0.0, 1.570795, 0.0

0.0, 1.570795, 1.570795

0.0, 0.0, 0.0

0.0, 0.0, 0.0

0.0, 0.0, 0.0

Monocular and Stereo Camera Calibration

The stereo calibration has been completed using more than 80 checkerboard image pairs taken using the stereo rig while placed in the aircraft. Using our AMCC Toolbox (an extension of Bouget's Camera Calibration Toolbox for Matlab and the RADDOC Toolbox), we have calibrated the stereo pair using the checkboard images given below in Calibration Data.

Intrinsic Calibration Parameters

Camera

Focal Length X,Y (pixels)

Principle Point (x,y) (pixels)

Distortions (K1,K2,P1,P2,K3)

Front

1641.99751, 1642.30964

642.15139, 470.34929

-0.19978, 0.13511, -0.00007, -0.00005, 0.00000

Back

1646.07299, 1645.39302

620.74483, 477.47527

-0.20465, 0.18856, -0.00111, 0.00040, 0.00000

Extrinsic Calibration Parameters

The rotation and translation homography between the stereo pair. Front camera is at the origin. The camera co-ordinate system is defined as follows: X left, Y up, Z forward (along optical axis).

Translation, t (x, y, z, in mm)

Rotation, r (radians)

Rotation matrix

6.09478, -775.96641, 7.36704

-0.01112, 0.03024, 0.00331

0.9995 -0.0035 0.0302
0.0031 0.9999 0.0112
-0.0302 -0.0111 0.9995

  • Please note that while both the checkerboard and dataset images for each camera are rotated by 180 degrees relative to each other, the calibration is performed on images that are rotated so that both cameras are aligned correctly.
  • Please note that while this calibration is correct on the ground, vibration and stress conditions in the air mean that the extrinsic calibration is not correct while in flight. Therefore, rectifying or using epipolar line matching will not work with this dataset in flight. These numbers are provided here as a guide only.

Calibration Data

The data used to calibrate the stereo dataset is provided here for your convenience if you would like to perform your own calibration. The stereo images containing multiple views of a checkerboard are provided in 101215_151454_MultiCamera0_calibration.rar.
If you would like to use our calibration you can download the monocular and stereo calibration files here that are compatible with Bouget's Camera Calibration for Matlab. If you wish to use OpenCV or our multicamera_data_player app (see below) to undistort the imagery, we have provided convenient XMLs with the data that OpenCV can import directly.

Getting started: Getting, uncompressing and debayering image files

  1. Download the 100831_155323_MultiCamera0_subset_db.rar file. This contains a small subset of processed data from the dataset ('db' = 'debayered'). Extract and examine the imagery to see if it suits your purposes.
  2. Download the 100831_155323_MultiCamera0_subset.rar file. This contains the same small subset as in the full size dataset, but the images are in their raw form. This allows you to experiment with your own image processing and do some experimental evaluation before committing to downloading the whole dataset.
  3. Extract 100831_155323_MultiCamera0_subset.rar using WinRAR on Windows or your favourite package unzipper in Linux. These should uncompress into a single folder titled 100831_155323_MultiCamera0_subset. Keep a note of the path of this folder.
    The images provided in the subset and larger whole dataset require some post-processing before they are useful. Firstly, the images are in a bayer format, which means that they appear as a speckled greyscale image. However, colour information is encapsulated within the image encoding, and can be extracted using a software package such as OpenCV. The images also have not yet been undistorted nor rectified. The following steps allow you to debayer, undistort and rectify the images according to your needs with a single executable.
  4. Download MultiCameraDataPlayer (or its source and dependencies, then build the application).
  5. Download the intrinsics and distortion xml files for the data (see Calibration)
  6. Place all four intrinsics and data files in a single folder called intrinsics or something similar. Keep a note of the path of this folder.
  7. Run MultiCameraDataPlayer using the examples provided on it's download page as guidance. For most purposes you will want to debayer and undistort the imagery and export to a video file format for ease of use.
  8. Finished! Now run your visual odometry algorithm on the processed dataset.
  9. When you are satisfied with the quality of the evaluation set, download all 12 .RAR files of the main dataset (see Datasets) containing the images. These are compressed in sizes of just under 2GB to fit browser size limitations.
  10. Extract the files as a group using WinRAR on Windows or your favourite package unzipper in Linux. These should uncompress into a single folder titled 100831_155323_MultiCamera0. Keep a note of the path of this folder.
  11. Run MultiCameraDataPlayer on the sequence you wish to evaluate and process for use in your visual odometry software

Additional information

Orca Playback

The data has been recorded using the Orca Robotics package. Placing all the log files in the same directory as the 101215_153851_MultiCamera0 directory and calling Orca's logplayer on the data will allow you to playback and re-export the data as you see fit.

Timestamping

  • Images are timestamped at the point of entry to the DMA buffer, this means that the timestamps will vary slightly but are guaranteed to be synchronised within 125 uS of each other as specified by the firewire protocol.
  • Timestamps for the Ins0, Gps0 and Imu0 logs are transferred from the Xsens according to GPS UTC time.
  • Timestamps for the Gps1 log is transferred from the NMEA GPS according to GPS UTC time.
    The system used to record data is non real-time, using the internal system clock, therefore timestamping may be innacurrate. We generally assume that timestamps are accurate within at least 100mS, often better.

File formats

GPS

Data Type

Timestamp (seconds)

Timestamp (milliseconds)

UTC Time Hours

UTC Time Minutes

UTC Time Second

Latitude (degrees)

Longitude (degrees)

Altitude (degrees)

Horizontal Position Error

Vertical Position Error

Heading

Speed

Climb rate

Satellites

Observations on L1

Observations on L2

Position Type

Geoidal Seperation

Example

1292391531

313628

0

0

0.000000

-27.492475400000

153.011470600000

42.78900

7.01850

0.00000

0.00000

0.00000

0.00000

0

0

0

1

0.00000

INS

Data Type

Timestamp (seconds)

Timestamp (milliseconds)

Latitude (degrees)

Longitude (degrees)

Altitude (m)

Height AMSL (m)

vENU X

vENU Y

vENU Z

Roll (rad)

Pitch (rad)

Yaw (rad)

Example

1292391532

94359

-27.492476105690

153.011469721794

43.187838614

43.187838614

-0.189469711

-0.018373683

0.318927496

0.014188348

-0.026663725

1.282561681

IMU

Data Type

Timestamp (seconds)

Timestamp (milliseconds)

X Acceleration (m)

Y Acceleration (m)

Z Acceleration (m)

Gyro X Acceleration (rad)

Gyro Y Acceleration (rad)

Gyro Z Acceleration (rad)

Example

1292391532

94299

-0.164379

0.129229

-9.68359

-0.00312483

-0.00254386

-0.00429477

MultiCamera

First Line (where columns 2-22 are repeated for each camera)

Data Type

Total Number of Cameras

Cam 0 Expected Image Width (pixels)

Cam 0 Expected Image Height (pixels)

Cam 0 Data format

Cam 0 Frame Rate (Hz)

Cam 0 X offset (m)

Cam 0 Y offset (m)

Cam 0 Z offset (m)

Cam 0 Roll offset (rad)

Cam 0 Pitch offset (rad)

Cam 0 Yaw offset (rad)

 

 

 

Cam 0 Focal Length Fx (pixels)

Cam 0 Focal Length Fy (pixels)

Cam 0 Principle Point cx (pixels)

Cam 0 Principle Point cy (pixels)

Cam 0 k1

Cam 0 k2

Cam 0 p1

Cam 0 p2

Cam 1 Expected Image Width (pixels)

Cam 1 Expected Image Height (pixels)

Cam 1 Data format

Cam 1 Frame Rate (Hz)

Cam 1 X offset (m)

Cam 1 Y offset (m)

Cam 1 Z offset (m)

Cam 1 Roll offset (rad)

Cam 1 Pitch offset (rad)

Cam 1 Yaw offset (rad)

 

 

 

Cam 1 Focal Length Fx (pixels)

Cam 1 Focal Length Fy (pixels)

Cam 1 Principle Point cx (pixels)

Cam 1 Principle Point cy (pixels)

Cam 1 k1

Cam 1 k2

Cam 1 p1

Cam 1 p2

Example

2

1024

768

GRAY8

30

0

0.379

0

0

0

0

0

0

0

0

0

0

0

0

0

0

0

1024

768

GRAY8

30

0

-0.371

0

0

0

0

0

0

0

0

0

0

0

0

0

0

0

All subsequent lines. Columns 3-5 are repeated for each camera and column 6 is repeated afterwards

Data Type

Cam 0 Timestamp (seconds)

Cam 0 Timestamp (milliseconds)

Cam 0 Image Width (pixels)

Cam 0 Image Height (pixels)

Cam 0 Data format

Cam 1 Timestamp (seconds)

Cam 1 Timestamp (milliseconds)

Cam 1 Image Width (pixels)

Cam 1 Image Height (pixels)

Cam 1 Data format

Cam 0 Relative Image Location and Name

Cam 1 Relative Image Location and Name

Example

1292391532

101549

1024

768

GRAY8

1292391532

101521

1024

768

GRAY8

.//101215_153851_MultiCamera0//cam0_image00001.bmp

.//101215_153851_MultiCamera0//cam1_image00001.bmp

Credits

Dataset Authors

Michael Warren michael.warren@qut.edu.au
Ben Upcroft ben.upcroft@qut.edu.au
Michael Shiel michael.shiel@qut.edu.au

Please direct any dataset queries or issues to Michael Warren.