This paper introduces a new process, environment matting, which captures not just a foreground object and its traditional opacity matte from a real-world scene, but also a descrip...
Douglas E. Zongker, Dawn M. Werner, Brian Curless,...
We present an efficient colon flattening algorithm using conformal structure, which is angle-preserving and minimizes the global distortion. Moreover, our algorithm is general w...
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
In this paper, we present an approach for video surveillance involving (a) moving object detection, (b) tracking and (c) normal/abnormal event recognition. The detection step uses...
Shadow detection is critical for robust and reliable vision-based systems for traffic vision analysis. Shadow points are often misclassified as object points causing errors in loc...