— Context is critical for reducing the uncertainty in object detection. However, context modelling is challenging because there are often many different types of contextual infor...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
Abstract. Computer vision algorithms for individual tasks such as object recognition, detection and segmentation have shown impressive results in the recent past. The next challeng...
ns to define the abstract modelling language that determines the structure of the models that are to be used a two-step meta-modelling approach turned out as most adequate. In the ...
In this paper we present an adaptive but robust object
detector for static cameras by introducing classifier grids.
Instead of using a sliding window for object detection we
pro...
Peter M. Roth, Sabine Sternig, Helmut Grabner, Hor...