Dataset

Crowd counting database

Queensland University of Technology
Dr David Ryan (Aggregated by) Dr Simon Denman (Aggregated by)
Viewed: [[ro.stat.viewed]] Cited: [[ro.stat.cited]] Accessed: [[ro.stat.accessed]]
ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rfr_id=info%3Asid%2FANDS&rft_id=info:doi10.4225/09/5858bfb708148&rft.title=Crowd counting database&rft.identifier=10.4225/09/5858bfb708148&rft.publisher=Queensland University of Technology&rft.description=This dataset was collected for an assessment of a crowd counting alogorithm. The dataset is a vision dataset taken from a QUT Campus and contains three challenging viewpoints, which are referred to as Camera A, Camera B and Camera C. The sequences contain reflections, shadows and difficult lighting fluctuations, which makes crowd counting difficult. Furthermore, Camera C is positioned at a particularly low camera angle, leading to stronger occlusion than is present in other datasets.The QUT datasets are annotated at sparse intervals: every 100 frames for cameras B and C, and every 200 frames for camera A as this is a longer sequence. Testing is then performed by comparing the crowd size estimate to the ground truth at these sparse intervals, rather than at every frame. This closely resembles the intended real-world application of this technology, where an operator may periodically ‘query’ the system for a crowd count. Due to the difficulty of the environmental conditions in these scenes, the first 400-500 frames of each sequence is set aside for learning the background model.&rft.creator=QUT SAIVT: Speech, audio, image and video technologies research &rft.date=2012&rft.edition=1&rft.coverage=153.025013,-27.476409&rft_rights=© Queensland University of Technology, 2012&rft_rights=Creative Commons Attribution-Share Alike 3.0 http://creativecommons.org/licenses/by-sa/3.0/au/&rft_subject=Artifical Intelligence and Image Processing&rft_subject=Computer Vision&rft_subject=Local Features &rft_subject=Density Estimation &rft_subject=Image Processing&rft_subject=Engineering&rft_subject=Crowd Monitoring&rft_subject=Crowd Counting &rft_subject=Signal Processing&rft_subject=Scene Invariant &rft_subject=Information and Computing Sciences&rft.type=dataset&rft.language=English Access the data

Licence & Rights:

Open Licence view details
CC-BY-SA

Creative Commons Attribution-Share Alike 3.0
http://creativecommons.org/licenses/by-sa/3.0/au/

© Queensland University of Technology, 2012

Access:

Other view details

In addition to citing our paper, we kindly request that the following text be included in an acknowledgements section at the end of your publications:We would like to thank the SAIVT Research Labs at Queensland University of Technology (QUT) for freely supplying us with the SAIVT-QUT Crowd Counting database for our research.

Contact Information

Postal Address:
David Ryan

david.ryan@qut.edu.au

Full description

This dataset was collected for an assessment of a crowd counting alogorithm.

The dataset is a vision dataset taken from a QUT Campus and contains three challenging viewpoints, which are referred to as Camera A, Camera B and Camera C. The sequences contain reflections, shadows and difficult lighting fluctuations, which makes crowd counting difficult. Furthermore, Camera C is positioned at a particularly low camera angle, leading to stronger occlusion than is present in other datasets.

The QUT datasets are annotated at sparse intervals: every 100 frames for cameras B and C, and every 200 frames for camera A as this is a longer sequence. Testing is then performed by comparing the crowd size estimate to the ground truth at these sparse intervals, rather than at every frame. This closely resembles the intended real-world application of this technology, where an operator may periodically ‘query’ the system for a crowd count.

Due to the difficulty of the environmental conditions in these scenes, the first 400-500 frames of each sequence is set aside for learning the background model.

Click to explore relationships graph

153.025013,-27.476409

153.025013,-27.476409

Identifiers