This work contributes to the robotic bin-picking problem, and more specifically to the problem of localizing piled box-like objects. We employ range imagery, and use box-like Supe...
This paper describes a viewpoint invariant learningbased method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal wit...
We present various kinds of variational PDE based methods to interpolate missing sinogram data for tomographic image reconstruction. Using the observed sinogram data we inpaint th...
A novel filter feature selection technique is introduced. The method exploits the information conveyed by the evolution of the training samples weights similarly to the Adaboost a...
In this paper we propose an alternative interpretation of Bayesian learning based on maximal evidence principle. We establish a notion of local evidence which can be viewed as a c...