Campus Map

A Large-Scale Dataset to Support Multi-View VO, SLAM and BEV Estimation

James Ross
Nimet Kaygusuz
Oscar Mendez
Richard Bowden

Centre for Vision, Speech and Signal Processing
University of Surrey
Guildford, UK

Campus Map is an automotive dataset comprising 22 driving and parking sequences collected around the University of Surrey campus and its car park. 6 cameras provide 360° coverage around the vehicle. Trajectories have been reconstructed from 64-beam LiDAR and 5 Hz GPS.

The dataset is provided by the University of Surrey, CVSSP under CC BY-NC-SA 4.0. In short, you can use and adapt it for non-commercial purposes but please cite our paper:

@inproceedings{campusmap,
  author={Ross, James and Kaygusuz, Nimet and Mendez, Oscar and Bowden, Richard}, 
  title={Campus Map: A Large-Scale Dataset to Support Multi-View VO, SLAM and BEV Estimation},
  booktitle={2024 IEEE International Conference on Robotics and Automation (ICRA)} 
  year={2024}}

Data

Download: All data (ROS bags)

Or, you can download subsets of the data or individual sequences below.


Subsets

All driving sequences ROS bags
All parking sequences ROS bags
Bird's Eye View (BEV) semantic maps LMDBs

The following tools are also available:

Python development kit Download
Automotive simulator Available on GitLab

Individual Sequences

Campus Only

A Driving 9 m 31 s ROS bags
B Driving 5 m 35 s ROS bags
C Driving 6 m 52 s ROS bags
D Driving 10 m 40 s ROS bags
E Driving 6 m 44 s ROS bags

Campus and Car Park

F Driving 13 m 5 s ROS bags

Car Park Only

G Driving & Parking 49 m 22 s ROS bags
H Driving & Parking 38 m 41 s ROS bags
I Parking 6 m 25 s ROS bags
J Parking 2 m 30 s ROS bags
K Parking 4 m 32 s ROS bags
L Parking 5 m 42 s ROS bags
M Parking 2 m 2 s ROS bags
N Parking 2 m 13 s ROS bags
O Parking 5 m 25 s ROS bags
P Parking 3 m 12 s ROS bags
Q Parking 5 m 25 s ROS bags
R Driving & Parking 9 m 43 s ROS bags
S Parking 4 m 59 s ROS bags
T Parking 4 m 46 s ROS bags
U Parking 5 m 24 s ROS bags
V Parking 5 m 21 s ROS bags

Contact

Please direct any concerns with the dataset or download page to j.ross@surrey.ac.uk.