We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....
This paper proposes an automatic foreground segmentation system based on Gaussian mixture models and dynamic graph cut algorithm. An adaptive perpixel background model is develope...
In this paper we describe a hybrid approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature s...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...
EffecTV is a real-time software video effect processor based on motion detection and image processing techniques. EffecTV was released in 2001 as an open source software, and has b...
Abstract-- We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approac...
Bastian Leibe, Konrad Schindler, Nico Cornelis, Lu...