When creating a digital composite of, for example, two people standing side-by-side, it is often difficult to match the lighting conditions from the individual photographs. Lighti...
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...
Recognizing categories of articulated objects in real-world scenarios is a challenging problem for today's vision algorithms. Due to the large appearance changes and intra-cla...
We have developed a method that can discriminate anomalous image sequences for more efficiently utilizing security videos. To match the wide popularity of security cameras, the me...
The purpose of this paper is to estimate the position of a human in the image frame and to use this information to diagnose falls. A nonholonomic locomotion model describes the dis...