Tilman Wekel

Learn More
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 feature(More)
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 are(More)
Recent advances in 3D reconstruction allows 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 modeling, or rendering requires more advanced(More)
In this paper, an approach for learning of crawling movements of a four-legged autonomous robot is presented. On the basis of a self-supervised strategy, the robot learns to choose its next movement by its sensorimotor states. This is based on feedback gained from the environment by actively tracking an object. Within a few hours of training, the robot(More)
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 recover(More)
  • 1