The MIIS Eprints Archive

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

Ward, Jonathan and Antonucci, Giancarlo and Barter, Edmund and Brooks-Tyreman, Frank and Connaughton, Colm and Coughlan, Michael and Kuhne, Ronja and Kaiser, Marcus and Wang, Victor (2018) Evaluation of the Accuracy of a Computer-Vision Based Crowd Monitoring System. [Study Group Report]

[img] PDF


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 distortion due to a fisheye lens. We also develop a statistical model of human counting errors and attempt to estimate human accuracy from data. Finally, we attempt to relate human and computer accuracy on the basis of simplifying statistical approximations.

Item Type:Study Group Report
Problem Sectors:Information and communication technology
Study Groups:European Study Group with Industry > ESGI 138 (Bath, UK, July 16-20, 2018)
UK Study Groups > ESGI 138 (Bath, UK, July 16-20, 2018)
Company Name:CrowdVision
ID Code:755
Deposited By: Bogdan Toader
Deposited On:11 May 2019 14:02
Last Modified:11 May 2019 14:02

Repository Staff Only: item control page