The use of depth is becoming increasingly popular in real-time computer vision applications. However, when using real-time stereo for depth, the quality of the disparity image is ...
Recognition of player actions in broadcast sports video is a challenging task due to low resolution of the players in video frames. In this paper, we present a novel method to rec...
In this work we evaluate the implementation of a video encoder based on the 3D Wavelet Transform optimized for HyperThreading technology and SMPs. We design several implementation...
Abstract This paper focuses on human behavior recognition where the main problem is to bridge the semantic gap between the analogue observations of the real world and the symbolic ...
We present a novel 3D model-based distributed video coding algorithm. It is based on independent, model-based tracking of multiple sources and distributed coding of the tracked fe...