DocumentCode
1304611
Title
Exposing Digital Forgeries in Ballistic Motion
Author
Conotter, Valentina ; O´Brien, James F. ; Farid, Hany
Author_Institution
Dept. of Eng. & Comput. Sci., Univ. of Trento, Trento, Italy
Volume
7
Issue
1
fYear
2012
Firstpage
283
Lastpage
296
Abstract
We describe a geometric technique to detect physically implausible trajectories of objects in video sequences. This technique explicitly models the three-dimensional ballistic motion of objects in free-flight and the two-dimensional projection of the trajectory into the image plane of a static or moving camera. Deviations from this model provide evidence of manipulation. The technique assumes that the object´s trajectory is substantially influenced only by gravity, that the image of the object´s center of mass can be determined from the images, and requires that any camera motion can be estimated from background elements. The computational requirements of the algorithm are modest, and any detected inconsistencies can be illustrated in an intuitive, geometric fashion. We demonstrate the efficacy of this analysis on videos of our own creation and on videos obtained from video-sharing websites.
Keywords
Web sites; cameras; computer forensics; fraud; image sequences; motion estimation; object detection; video signal processing; background elements; digital forgeries; free-flight projection; image plane; motion estimation; moving camera; physically implausible object trajectory detection; static camera; three-dimensional ballistic motion; two-dimensional trajectory projection; video sequences; video-sharing Web sites; Cameras; Equations; Estimation; Forensics; Projectiles; Security; Trajectory; Digital forensics; video forensics;
fLanguage
English
Journal_Title
Information Forensics and Security, IEEE Transactions on
Publisher
ieee
ISSN
1556-6013
Type
jour
DOI
10.1109/TIFS.2011.2165843
Filename
5995165
Link To Document