We propose a novel learning algorithm to detect moving pedestrians from a stationary camera in real-time. The algorithm learns a discriminative model based on eigenflow, i.e. the ...
This paper presents a fast disparity analysis approach based on a hybrid block- and pixel-recursive matching scheme. The key idea is to choose efficiently a small number of candid...
Peter Kauff, Nicole Brandenburg, Michael Karl, Oli...
This paper presents a novel surveillance video indexing and retrieval system based on object features similarity measurement. The system firstly extracts moving objects from the vi...
Jacky S-C. Yuk, Kwan-Yee Kenneth Wong, Ronald H. Y...
We present a new method to robustly and efficiently analyze foreground when we detect background for a fixed camera view by using mixture of Gaussians models and multiple cues. Th...
This article deals with facial segmentation and liptracking with feedback control for real-time animation of a synthetic 3D face model. Classical approaches consist in two success...