Statistical background modelling and subtraction has proved to be a popular and effective class of algorithms for segmenting independently moving foreground objects out from a sta...
This paper introduces a new concept of surveillance, namely, audio-visual data integration for background modelling. Actually, visual data acquired by a fixed camera can be easily ...
Filtering based algorithms have become popular in tracking human body pose. Such algorithms can suffer the curse of dimensionality due to the high dimensionality of the pose state ...
Rui Li, Ming-Hsuan Yang, Stan Sclaroff, Tai-Peng T...
This contribution addresses the problem of obtaining photorealistic 3D models of a scene from images alone with a structure-from-motion approach. The 3D scene is observed from mul...
We consider the problem of continuously maintaining order sketches over data streams with a relative rank error guarantee . Novel space-efficient and one-scan randomised technique...