Video surveillance systems seek to automatically identify events of interest in a variety of situations. Extracting a moving object from background is the most important step of t...
This paper presents a simple and effective nonparametric approach to the problem of image parsing, or labeling image regions (in our case, superpixels produced by bottom-up segmen...
This paper discusses a new method for capturing the complete appearanceof both synthetic and realworld objects andscenes,representing this information, and then using this represe...
Steven J. Gortler, Radek Grzeszczuk, Richard Szeli...
—We present a method to determine 3D motion and structure of multiple objects from two perspective views, using adaptive Hough transform. In our method, segmentation is determine...
We present a novel variational method for the simultaneous estimation of dense scene flow and structure from stereo sequences. In contrast to existing approaches that rely on a ful...