Tilman Wekel

Tilman Wekel
Philips Technologie GmbH, Innovative Technologies, Research Laboratories

Dr.-Ing.

About

11
Publications
631
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
89
Citations
Additional affiliations
June 2009 - present
Technische Universität Berlin
Position
  • Researcher
January 2009 - May 2009
Technische Universität Berlin
Position
  • Researcher

Publications

Publications (11)
Conference Paper
Though a large body of computer vision research has investigated developing generic semantic representations, efforts towards developing a similar representation for 3D has been limited. In this paper, we learn a generic 3D representation through solving a set of foundational proxy 3D tasks: object-centric camera pose estimation and wide baseline f...
Conference Paper
Full-text available
Recent advances in 3D reconstruction enable to acquire highly detailed geometry from a set of images. The outcome of vision-based reconstruction methods is often oversampled, noisy, and without any higher-level information. Further processing such as object recognition, physical measurement, urban modelling, or rendering requires more advanced repr...
Thesis
Jüngste Fortschritte im Bereich der bildbasierten 3D-Rekonstruktion ermöglichen die Aqkuisition hochdetaillierter Modelle mithilfe von gewöhnlichen Digitalbildern. Die Ergebnisse solcher Systeme sind in der Regel unstrukturierte und redundante Daten wie Punktwolken oder triangulierte Oberflächen. Viele Anwendungen wie physikalische Messung, Renderi...
Conference Paper
Recent advances in 3D reconstruction allow to quickly acquire highly detailed and complex geometry. However, the outcome of such systems is usually unstructured, noisy and redundant. In order to enable further processing such as CAD modeling, physical measurement or rendering, semantic information about shape and topology needs to be derived from t...
Chapter
In this paper, a new and robust approach to mesh segmentation is presented. There are various algorithms which deliver satisfying results on clean 3D models. However, many reverse-engineering applications in computer vision such as 3D reconstruction produce extremely noisy or even incomplete data. The presented segmentation algorithm copes with thi...
Conference Paper
3D reconstruction is an important field in computer vision. Many approaches are based on multiple images of a given scene. Using only one single image is far more challenging. Monocular image reconstruction can still be achieved by using regular and symmetric structures, which often appear in human environment. In this work we derive two schemes to...
Conference Paper
In this paper a new approach to find an optimal surface representation is described. It is shown that the minimum description length (MDL) principle can be used to select a trade-off between goodness-of-fit and complexity of decimated mesh representations. A given mesh is iteratively simplified by using different decimation algorithms. At each step...
Conference Paper
Full-text available
In this paper a real time obstacle detection system for robots is presented. The technique is based on a single camera and no further sensors or encoders are required. The algorithm is independent of geometry and even moving objects can be detected. The system provides a top view map of the robotpsilas field of view in real-time. First, the images...
Conference Paper
In this paper an approach to estimate the topography of indoor environments is presented. The system is based on a single camera system only. The topography of areas is often a matter of particular interest and has a wide range of navigational application. The ground surface is assumed to be completely planar; this is usually satisfied in indoor en...

Network

Cited By