Video motion detection beyond reasonable doubt

  • Authors:
  • Zhuo Xiao;Amirsaman Poursoltanmohammadi;Matthew Sorell

  • Affiliations:
  • University of Adelaide SA, Australia;University of Adelaide SA, Australia;University of Adelaide SA, Australia

  • Venue:
  • Proceedings of the 1st international conference on Forensic applications and techniques in telecommunications, information, and multimedia and workshop
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We consider the analysis of surveillance video footage containing occasional activities of potential interest interspersed with long periods of no motion. Such evidence is problematic for three reasons: firstly, it takes up a great deal of storage capacity with little evidential value; secondly, human review of such surveillance is extremely time-consuming and subject to errors due to fatigue; and thirdly, there is often a need to prove to the satisfaction of the Court that excised footage contains no images of evidential value. We are therefore concerned with objective, reliable detection of video motion to automate the extraction of activities of interest and to provide simple but reliable measurements to the court to prove that this is a complete record of all activities in the footage. Early results indicate that average luminance-based detection is particularly reliable, and we provide a comparison with other frame-difference techniques.