We present a novel pedestrian detection system based on probabilistic component assembly. A part-based model is proposed which uses three parts consisting of head-shoulder, torso a...
Martin Rapus, Stefan Munder, Gregory Baratoff, Joa...
Abstract. The (Extended) Kalman filter has been established as a standard method for object tracking. While a constraining motion model stabilizes the tracking results given noisy...
Alexander Barth, Jan Siegemund, Uwe Franke, Wolfga...
In this paper, we address the problem of image sequence segmentation with dynamical shape priors. While existing formulations are typically based on hard decisions, we propose a fo...
The purpose of image segmentation is to partition the pixel grid of an image into connected components termed segments such that (i) each segment is homogenous and (ii) for any pai...
In this paper, we show that a better performance can be achieved by training a keypoint detector to only find those points that are suitable to the needs of the given task. We demo...
Christoph Strecha, Albrecht Lindner, Karim Ali, Pa...