Home	People	Research	Publications	Demos
News	Jobs	Prospective Students	About	Internal

Demo of Background Subtraction in Dynamic Scenes
These are demos of the background subtraction. The videos are in Quicktime format (H.264).Quicktime is a free software and can be downloaded from here Comparison with Other Background Subtraction Techniques
Video Results
[Skiing (15 MB)]	[Surf (15 MB)]	[Flock (15 MB)]
[Cyclists (15 MB)]	[Landing (15 MB)]	[Birds (15 MB)]
[Chopper (15 MB)]	[Surfers (15 MB)]	[Jump (15 MB)]
[Boat (15 MB)]	[Bottle (15 MB)]	[Hockey (15 MB)]
[Ocean (15 MB)]	[Zodiac (15 MB)]	[Freeway (15 MB)]
[Traffic (15 MB)]	[Rain (15 MB)]	[Peds (15 MB)]
Methods Compared Disc-Sal - the output of discriminant saliency detector (proposed) Kernel Density Estimate (KDE) - from A. Elgammal, R. Duraiswami, D. Harwood, and L. S. Davis. Background and foreground modeling using nonparametric kernel density for visual surveillance. In Proceedings of the IEEE, volume 90, pages 1151-1163, July 2002 Monnet - from A. Monnet, A. Mittal, N. Paragios, and V. Ramesh. Background modeling and subtraction of dynamic scenes. CVPR, 2003 Surprise - from L. Itti and P. Baldi. A principled approach to detecting surprising events in video. CVPR, pages 631-637, 2005 Gaussian mixture model (GMM) - from Z. Zivkovic. Improved adaptive Gaussian mixture model for background subtraction. ICPR, 2004
Saliency Map Superimposed with Video Frames for Zodiac Sequence



© SVCL