This paper presents an Augmented Reality system for aiding a pump assembling process at Grundfos, one of the leading pump producers. Stable pose estimation of the pump is required in order to augment the graphics correctly. This is achieved by matching image edges with synthesized edges from CAD models. To ensure a system which operates at interactive-time the CAD models are pruned o -line and ...

The following report discusses my work at the IDIAP from 06.2007 to 08.2007. This work had for objective to build a classifier for cat images, and focused on difficult images. Two approaches were implemented; one was using the Chamfer distance metric for matching, and the other learned models of our training images and used the Kullback-Leibler divergence as a metric of image comparison. Noise ...

We present a template-based approach to detecting human silhouettes in a specific walking pose. Our templates consist of short sequences of 2D silhouettes obtained from motion capture data. This lets us incorporate motion information into them and helps distinguish actual people who move in a predictable way from static objects whose outlines roughly resemble those of humans. Moreover, during t...

Limited by the regular grids in computing, many modelling approaches (e.g. field-based methods) sample 3D shape insensitive to sharp features therefore exhibit aliasing errors, by which a lot of sharp edges and corners are lost on the reconstructed surface. An incremental approach for recovering sharp edges on an insensitive sampled triangular mesh is presented in this paper, so that shape appr...

In this paper a new fully automatic method for registration of intramodal medical data is proposed. The method combines edge detection at diierent thresholds with chamfer distance transformation. The result is a distance map which is weighted by the importance of the edges which are extracted. As an alternative to the user-dependent non-automatic registration methods this approach ooers a good ...

In earlier work [1], we demonstrated that cortical registration could be improved on simulated data by using blurred, geometric, image-based features (Lvv) or explicitly extracted and blurred sulcal traces on simulated data. Here, the technique is modified to incorporate sulcal ribbons in conjunction with a chamfer distance objective function to improve registration in real MRI data as well. Ex...

The Advanced Deburring and Chamfer System is robotic workcell designed to put precision chamfers on parts made with hard metals. The project was funded by the United States Navy so that the technology developed could be applied to their air defense systems. The Unified Telerobotic Architecture Project was a United States Air Force funded project to develop an open architecture for robotic appli...

The key-feature all additive manufacturing processes have in common is parts being built up in layers. Due to this tool-less build-up principle, the degree of freedom in design is huge compared to conventional manufacturing processes. For instance rear sections, inner cavities, conformal cooling-channels and lightweight-structures can be realized without a significant rise of manufacturing-cost...