2017-01-23T16:32:36 n7544

Surveillance footage for activity analysis in complicated scenes

Viewed: 123

This dataset, the SAIVT-Campus Database is an abnormal event detection database captured at the Queensland University of Technology, Australia. It contains two video files from real world surveillance footage without any actors. Each video file is one hour in duration. The normal activities include pedestrians entering or exiting the building, entering or exiting a lecture theatre (yellow door), and going to the counter at the bottom right. The abnormal events are caused by a heavy rain outside, and include people running in from the rain, people walking towards the door to exit and turning back, wearing raincoats, loitering and standing near the door and overcrowded scenes. The rain happens only in the later part of the test dataset. As a result, we assume that the training dataset only contains the normal activities.

Geographical area of data collection

kmlPolyCoords
153.025013,-27.476409

Publications

Xu, Jingxin, Denman, Simon, Fookes, Clinton B., & Sridharan, Sridha (2012) Activity analysis in complicated scenes using DFT coefficients of particle trajectories. In 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2012), 18-21 September 2012, Beijing, China. available at http://eprints.qut.edu.au/51041/

Research areas

DFT coefficients
Campus
complicated scenes
abnormal event

Cite this collection

Xu,Jingxin; Denman,Simon; Fookes,Clinton; Sridharan,Sridha. (2014): Surveillance footage for activity analysis in complicated scenes. [Queensland University of Technology]. https://doi.org/10.4225/09/5885a356bfbb2

Related information

Dataset also known as The SAIVT-Campus Database https://wiki.qut.edu.au/display/saivt/SAIVT-Campus+Database

Licence


Creative Commons Attribution-Share Alike 4.0 (CC-BY-SA)
http://creativecommons.org/licenses/by-sa/4.0/

Copyright

© Queensland University of Technology, 2012

Dates of data collection

From 2012-01-01 to 2013-12-31

Connections

Was collected by
Jingxin Xu   (Researcher)
Clinton Fookes  (Researcher)
Simon Denman  (Researcher)
Sridha Sridharan  (Researcher)

Contacts

Name: Jingxin Xu

Other

Data type:
Individually identifiable
Date record created:
2014-06-19T14:50:26
Date record modified:
2017-01-23T16:32:36
Record status:
Published - Open Access