Paper
13 October 2011 Investigation of the performance of video analytics systems with compressed video using the i-LIDS sterile zone dataset
Prashath Mahendrarajah
Author Affiliations +
Abstract
Recent years have seen significant investment and increasingly effective use of Video Analytics (VA) systems to detect intrusion or attacks in sterile areas. Currently there are a number of manufacturers who have achieved the Imagery Library for Intelligent Detection System (i-LIDS) primary detection classification performance standard for the sterile zone detection scenario. These manufacturers have demonstrated the performance of their systems under evaluation conditions using an uncompressed evaluation video. In this paper we consider the effect on the detection rate of an i-LIDS primary approved sterile zone system using compressed sterile zone scenario video clips as the input. The preliminary test results demonstrate a change time of detection rate with compression as the time to alarm increased with greater compression. Initial experiments suggest that the detection performance does not linearly degrade as a function of compression ratio. These experiments form a starting point for a wider set of planned trials that the Home Office will carry out over the next 12 months.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Prashath Mahendrarajah "Investigation of the performance of video analytics systems with compressed video using the i-LIDS sterile zone dataset", Proc. SPIE 8189, Optics and Photonics for Counterterrorism and Crime Fighting VII; Optical Materials in Defence Systems Technology VIII; and Quantum-Physics-based Information Security, 81890O (13 October 2011); https://doi.org/10.1117/12.916850
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Video

Video compression

Video surveillance

Analytics

Motion models

Cameras

Manufacturing

Back to Top