Real world computer vision systems highly depend on reliable, robust retrieval of motion cues to make accurate decisions about their surroundings. In this paper, we present a simp...
This paper presents a sensor management scheme based on maximizing the expected R´enyi Information Divergence at each sample, applied to the problem of tracking multiple targets. ...
Christopher M. Kreucher, Keith Kastella, Alfred O....
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...
In thispaper, the problem ofsimultaneousmotionestimation of multiple independently moving objects is addressed. A novel Bayesian approach is designedfor solvingthisproblem using t...
The problem considered in this paper is that of estimating the projective transformation between two images in situations where the image motion is large and featurematching is no...