Abstract Kernel-based object tracking refers to computing the translation of an isotropic object kernel from one video frame to the next. The kernel is commonly chosen as a primiti...
—This paper introduces a new sensory system for the 2-D detection, tracking, and prediction of human motions. Using the data acquired through the sensory system, a model of a hum...
—In this paper, we propose a method designed to allow creatures to actively respond to a fluid environment. We explore various objective functions in order to determine ways to ...
Michael Lentine, Jon Gretarsson, Craig A. Schroede...
Description
===========
This package contains the major source code of a demo for our learning based digital image matting technique (as detailed in the below paper).
@InPro...
The scene flow in binocular stereo setup is estimated using a seed growing algorithm. A pair of calibrated and synchronized cameras observe a scene and output a sequence of image...