Sebastian Gerke

Learn More
Object-oriented programming is the current mainstream programming paradigm but existing RDF APIs are mostly triple-oriented. Traditional techniques for bridging a similar gap between relational databases and object-oriented programs cannot be applied directly given the different nature of Semantic Web data, for example in the semantics of class membership,(More)
In this paper, a system for temporally consistent registration of a soccer field is proposed. It is implemented using 2D field line and arc detection as well as motion estimation for frames where too few field lines are detected. We show that a combination of these technologies yields more consistent results than common state-of-the-art approaches. As an(More)
When creating Semantic Web data, users have to make a critical choice for a vocabulary: only through shared vocabularies can meaning be established. A centralised policy prevents terminology divergence but would restrict users needlessly. As seen in collaborative tagging environments , suggestion mechanisms help terminology convergerce without forcing(More)
In this paper we present our approach to the 2011 ImageClef PhotoAnnotation task, which is based on the well known bag-of-words model. We investigated an approach for selecting the most informative training samples per concept for classification and the impact of fusing the OpponentSIFT feature with the GIST feature which calculates global image statistics,(More)
In this paper we present our approach to the 2010 ImageClef PhotoAnnotation task. Based on the well-known bag-of-words approach we suggest two extensions. First, we analyzed the impact of category specific features and classifiers. In order to classify quality-related image categories we implemented a sharpness measure and use this as additional feature in(More)
Currently, bag-of-words approaches for image categorization are very popular due to their relative simplicity, robustness and high efficiency. However, they lack the ability to represent the spatial composition of an image. This drawback has been addressed by several approaches, with spatial pyramids being the most popular. Spatial pyramids divide an image(More)
An analysis is conducted of the multipartite entanglement for Gaussian states generated by the parametric down-conversion of a femtosecond frequency comb. Using a recently introduced method for constructing optimal entanglement criteria, a family of tests is formulated for mode decompositions that extends beyond the traditional bipartition analyses. A(More)
Hydrogenated intrinsic amorphous silicon ((i) a-Si:H) layers deposited on n-type crystalline silicon (c-Si) by plasma enhanced chemical vapour deposition (PECVD) are investigated during long-time thermal treatment (100 h at 200°C) with regard to the depth profile of hydrogen in the a-Si layer and its diffusion into the c-Si bulk. The morphology of the (i)(More)
Thick (150 nm) hydrogenated intrinsic amorphous silicon ((i) a-Si:H) layers, which are deposited with different recipes on crystalline silicon (c-Si) by plasma enhanced chemical vapour deposition (PECVD) are investigated by minority carrier lifetime measurements (τ eff) and capacitance-voltage C(V) spectroscopy during thermal treatment. The minority carrier(More)
Player detection in sports video is a challenging task: In contrast to typical surveillance applications, a pan-tilt-zoom camera model is used. Therefore, simple background learning approaches cannot be used. Furthermore, camera motion causes severe motion blur, making gradient based approaches less robust than in settings where the camera is static. The(More)