This paper describes a method for articulated upper body tracking in monocular scenes. The compatibility between model and the image is estimated using one particle filter for eac...
Visual data comprises of multi-scale and inhomogeneous signals. In this paper, we exploit these characteristics and develop an adaptive data approximation technique based on a hie...
Misregistration between the color separations of a printed image, which is often inevitable, can cause objectionable color shifts in average color. We analyze the impact of inter-...
A considerable amount of work in larger film and video restoration projects is dedicated to manually exploring the audiovisual content in order to estimate the costs for restorati...
Discrete tomography (DT) is concerned with the tomographic reconstruction of images that consist of only a small number of gray levels. DT reconstruction problems are usually unde...
The segmentation and recognition modules are usually implemented sequentially in most traditional automatic license recognition (LPR) systems. In this work, we integrate segmentat...
A key goal of far-field activity analysis is to learn the usual pattern of activity in a scene and to detect statistically anomalous behavior. We propose a method for unsupervised...
In this paper, we propose an algorithm for identifying regions of interest (ROIs) in video, particularly for the keyframes extracted from a home video. The camera motion is introd...
This paper deals with conversion from H.264/AVC (Advanced Video Coding) coded video into the MPEG-2 format. The proposed approach exploits similarities between the coding techniqu...
Multi-projector super-resolution is the dual of multi-camera superresolution. The goal of projector super-resolution is to produce a high resolution frame via superimposition of m...