We present an approach to tracking human activities in a monocular video. We model the human body by decomposing it into torso and limbs and use simple 3D shapes to approximate th...
Multiview video coding (MVC) is getting more and more attention in recent years because of the realistic perception it can bring. However, the current H.264-based coding scheme ca...
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...
Preserving historic recording on gramophone records is an important task because the traditional record play back system damages/wears out records eventually. We present an optica...
In this paper we describe a multi-modal ear and face biometric system. The system is comprised of two components: a 3D ear recognition component and a 2D face recognition componen...