Vision and GPS data for testing Open FABMAP's application to ground based, aerial and temporal mapping
Viewed:
3150
The data records a single route taken through the suburb of St Lucia, Queensland, Australia. The route was traversed at five different times of the day to
capture the difference in appearance between early morning and late
afternoon. The route was traversed again, another five times, two weeks
later for a total of ten datasets.
The data was recorded with a forward facing webcam attached to the roof of a car.
GPS data is included for each dataset.
Each dataset is labelled with the date and time it was collected in the following format DD/MM/YY_24HOUR. Each dataset has 5 files.
The data was recorded with a forward facing webcam attached to the roof of a car.
GPS data is included for each dataset.
Each dataset is labelled with the date and time it was collected in the following format DD/MM/YY_24HOUR. Each dataset has 5 files.
- (webcam_video.avi) video imagery. This file is compressed and no uncompressed version is available.
- (gps_log.txt) raw GPS data as logged
- (frame_log.txt) time stamps of each video frame compatible with GPS data
- (fGPS.txt) processed version of GPS and frame time stamps providing the GPS point for each frame in the video file
- (fGPS.mat) as above, saved for easy importation to MATLAB
Access rights
This dataset has been released for free and public use.
Location of data collection
kmlPolyCoords
153.023057,-27.488689 152.990445,-27.488689 152.990445,-27.507810 153.023057,-27.507810 153.023057,-27.488689
Publications
Glover, Arren, Maddern, William, Warren, Michael, Stephanie, Reid, Milford, Michael, & Wyeth, Gordon (2012). OpenFABMAP : an open source toolbox for appearance-based loop closure detection. Paper presented at The International Conference on Robotics and Automation. Retrieved from
http://eprints.qut.edu.au/50317/
Research areas
SLAM
Robotics
Adaptive Agents and Intelligent Robotics
FAB-MAP
Artifical Intelligence and Image Processing
Engineering
Spatial Data
Computer Vision
Information and Computing Science
Cite this collection
Glover, Arren, Maddern, William, Milford, Michael, & Wyeth, Gordon (2010). FAB-MAP + RatSLAM : appearance-based SLAM for multiple times of day. Paper presented at 2010 IEEE International Conference on Robotics and Automation (ICRA2010). Retrieved from
Glover, Arren, Maddern, William, Milford, Michael, & Wyeth, Gordon (2010) FAB-MAP + RatSLAM : appearance-based SLAM for multiple times of day. In: 2010 IEEE International Conference on Robotics and Automation (ICRA2010), 3 - 8 May 2010, Anchorage, Alaska, USA
Licence
Creative Commons Attribution-NonCommercial 4.0 (CC-BY-NC)
http://creativecommons.org/licenses/by-nc/4.0/
Copyright
Arren Glover and Will Maddern
Dates of data collection
From 2009-08-19 to 2009-09-11
Contacts
Email: aj.glover@qut.edu.au
Other
Date record created:
2014-02-09
Date record modified:
2015-06-11T21:31:15
Record status:
Published - Open Access