• Corpus ID: 195477121

Evaluation of the Accuracy of a Computer-Vision Based Crowd Monitoring System

@inproceedings{Ward2018EvaluationOT,
  title={Evaluation of the Accuracy of a Computer-Vision Based Crowd Monitoring System},
  author={Jonathan A. Ward and Giancarlo A. Antonucci and Edmund Barter and Frank Brooks-Tyreman and Colm Connaughton and Michael Coughlan and Ronja Kuhne and Marcus Kaiser and Victor Wang},
  year={2018}
}
Computer vision systems can be used to measure pedestrian flow rates, occupancy levels and queue times. It is difficult to assess the accuracy of such methods because the ground truth can be difficult to establish. Human counting is equally prone to error, even when using video recordings with no time constraints and the support of sophisticated software. In this report, we consider how errors may arise directly from the images recorded by the cameras, due to both occlusion of people and image… 
HKSiamFC: Visual-Tracking Framework Using Prior Information Provided by Staple and Kalman Filter
TLDR
Inspired by the key idea of a Staple tracker and Kalman filter, two more models are constructed to help compensate for SiamFC’s disadvantages and design a novel and robust tracking framework on the basis of Siam FC.

References

SHOWING 1-9 OF 9 REFERENCES
Pedestrian Counting Methods at Intersections
TLDR
Investigating the accuracy of three common counting methods indicates that manual counts with either sheets or clickers systematically underestimated pedestrian volumes.
Effectiveness of a Commercially Available Automated Pedestrian Counting Device in Urban Environments: Comparison with Manual Counts
High-quality continuous counts of pedestrian volume are necessary to evaluate the effects of pedestrian infrastructure investments and to improve pedestrian volume modeling. Automated pedestrian
Data-Driven Modeling of Pedestrian Crowds
TLDR
Video recordings from the crowd disaster in Mina, Kingdom of Saudi Arabia, where hundreds of pilgrims lost their lives during the annual Muslim pilgrimage to Makkah, gave the possibility to scientifically evaluate the dynamics of the crowd and empirically evaluate many of the previous assumptions used for pedestrian simulations.
An Investigation on the Manual Traffic Count Accuracy
Comparisons of count reproducibility
  • accuracy, and time to get results between a hemocytometer and the tc20 automated cell counter,” Bulletin, vol. 6003, pp. 1–4
  • 2013
generatingfunctionology: Third Edition
The Hungarian method for the assignment problem
  • 1955
and D
  • R. Ragland, “Pedestrian counting methods at intersections: a comparative study,” Transportation Research Record, vol. 2002, no. 1, pp. 26–30
  • 2007
Comparisons of count reproducibility , accuracy , and time to get results between a hemocytometer and the tc 20 automated cell counter
  • Bulletin
  • 2013