Warwick-NTU Multi-camera Forecasting (WNMF) database
This page introduces the Warwick-NTU Multi-camera Forecasting dataset (WNMF). If you would like to access the database, please use request access form at the bottom of this page. For code and further details, please see our GitHub repository: https://github.com/olly-styles/Multi-Camera-Trajectory-Forecasting
Dataset contents
The WNMF dataset contains footage of individuals traversing the Nanyang Technological University (NTU) campus. The dataset contains cross-camera tracking information, such that future trajectories of individuals can be anticipated across multiple camera views. The data was collected over a span of 20 days using 15 different CCTV cameras. This was not a controlled collection (i.e., it was collected in real-world conditions).
Raw data statistics:
We release camera entrance and departure videos, pre-computed tracking information and RE-ID features. Faces are blurred using the RetinaFace algorithm [1] to detect faces. Provided are the 4 seconds proceeding a camera departure event and 12 seconds following a camera entrance event, totally 16 seconds for each verified cross-camera match.
|
Hours of footage |
600 |
|
Number of cameras |
15 |
|
Collection period |
20 days |
|
Time period |
8:30am – 7:30pm |
|
Video resolution |
1920 by 1080 |
|
Frames per second |
5 |
|
Cross camera matches |
13.2K |
Released data statistics:
|
Hours of footage |
10.2 |
|
Cross-camera matches after verification |
2.3K |
|
Mean cross-camera RE-IDs per track |
2.08 |
How to obtain the dataset:
To download the dataset, please see the request access form at the bottom of this page.
Sample videos
|
Camera departure example (tracking data shown) |
Camera entrance example (tracking data hidden) |
|
|
|
Usage for Academic Research
This video dataset is released for academic research only, and is free to researchers from educational or research institutes for non-commercial purposes.
Citation
All publications using the WNMF dataset should include the following acknowledgement: “(Portions of) the research in this paper used the WNMF Dataset made available by the SIP Lab at the University of Warwick, United Kingdom, and the ROSE Lab at the Nanyang Technological University, Singapore.”
Any publications that result from using the WNMF dataset should cite the following paper: Olly Styles, Tanaya Guha, Victor Sanchez, Alex C. Kot, “Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras”, IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2020
If interested, please click on the "Request Dataset" hyperlink below for a copy of the Release Agreement. With your acceptance of the agreement, we will then send you the LoginID and password to the dataset.
Request Dataset
*Link to release agreement* https://github.com/olly-styles/Multi-Camera-Trajectory-Forecasting/blob/master/WNMF%20release%20agreement.pdf
*Link to request dataset* https://github.com/olly-styles/Multi-Camera-Trajectory-Forecasting
References
[1] Deng, J., Guo, J., Zhou, Y., Yu, J., Kotsia, I. and Zafeiriou, S., 2019. Retinaface: Single-stage dense face localisation in the wild. arXiv preprint arXiv:1905.00641.