This paper presents a multi-view approach to the tracking of people location and orientation. To achieve efficient and accurate likelihood evaluation, a novel likelihood computat...
In this paper we propose a new segmentation algorithm which combines patch-based information with edge cues under a probabilistic framework. We use a mixture of multiple Gaussians...
This paper proposes an efficient region-based background subtraction technique using static camera for motion detection in various monitoring applications. Color histograms, textu...
Parisa Darvish Zadeh Varcheie, Michael Sills-Lavoi...
—We propose an automatic approach to soft color segmentation, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesiz...
We present a simple but efficient model for object segmentation in video scenes that integrates motion and color information in a joint probabilistic framework. Optical flow is mo...