Skip to main content
padlock icon - secure page this page is secure

Open Access Statistical Sequential Analysis for Object-based Video Forgery Detection

Download Article:
 Download
(PDF 2,032 kb)
 
Over the years, video surveillance systems have been used for indisputable evidence of a crime. Unfortunately, videos of the surveillance systems can be forged through adding (deleting) an object to (from) a video scene (i.e., object-based forgery) with invisible traces and little effort. In this paper, we propose a novel approach that uses spatial decomposition, temporal filtering, and sequential analysis to detect object-based video forgery and estimate a movement of removed objects. The results show that our approach not only outperforms a previous approach in detecting forged videos but it is also more robust against compressed and lower resolution videos. Also, our approach can effectively estimate a movement of different sizes of removed objects.
No References for this article.
No Supplementary Data.
No Article Media
No Metrics

Keywords: Object based video forgery; Sequential analysis; Spatiotemporal analysis; Temporal change detection; Video forensics

Document Type: Research Article

Publication date: January 13, 2019

This article was made available online on January 13, 2019 as a Fast Track article with title: "Statistical sequential analysis for object-based video forgery detection".

More about this publication?
  • For more than 30 years, the Electronic Imaging Symposium has been serving those in the broad community - from academia and industry - who work on imaging science and digital technologies. The breadth of the Symposium covers the entire imaging science ecosystem, from capture (sensors, camera) through image processing (image quality, color and appearance) to how we and our surrogate machines see and interpret images. Applications covered include augmented reality, autonomous vehicles, machine vision, data analysis, digital and mobile photography, security, virtual reality, and human vision. IS&T began sole sponsorship of the meeting in 2016. All papers presented at EIs 20+ conferences are open access.

    Please note: For purposes of its Digital Library content, IS&T defines Open Access as papers that will be downloadable in their entirety for free in perpetuity. Copyright restrictions on papers vary; see individual paper for details.

  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more