This paper investigates the combination of spatial and probabilistic models for reasoning about pedestrian behaviour in visual surveillance systems. Models are learnt by a multi-s...
We present an iterative approximate solution to the multidimensional assignment problem under general cost functions. The method maintains a feasible solution at every step, and i...
Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with c...
Harold Christopher Burger, Christian J. Schuler, S...
3D reconstruction from an unordered set of images may fail due to incorrect epipolar geometries (EG) between image pairs arising from ambiguous feature correspondences. Previous m...
In this paper we present a novel method for foreground segmentation. Our proposed approach follows a nonparametric background modeling paradigm, thus the background is modeled by ...
Martin Hofmann 0011, Philipp Tiefenbacher, Gerhard...