Papers by Author: Sabina Jeschke

Abstract: Edges are crucial features for object segmentation and classification in both image and point cloud processing. Though many research efforts have been made in edge extraction and enhancement in both areas, their applications are limited respectively owing to their own technical properties. This paper presents a new approach to integrating the edge pixels in the 2D image into boundary data in the 3D point cloud by establishing the mapping relationship between these two types of data to represent the 3D edge features of the object. The 3D edge extraction based on the adoption of Microsoft Kinect as a 3D sensor - involves the following three steps: first, the generation of a range image from the point cloud of the object, second the edge extraction in the range image and edge extraction in the digital image, and finally edge data integration by referring to the correspondence map between point cloud data and image pixels.

Abstract: The increasing complexity of products and consumer interests is facing more and more challenges to production planning. An innovative approach, which facilitates efficient planning, is represented by a model-based approach using the concept of the Digital Factory. In order to realize the vision of virtual production, modular solutions like simulations or optimization tools are merged into a holistic model that provides a digital mapping of the entire production process. In this work, a framework is described, which is capable to integrate planning modules by using an integrative information model. Based on intelligence approaches, multiple data is linked to reach a vertical integration of the information flow. These cross-linked data structures facilitate a consolidation of data from different levels of the production monitoring and management layers. The provided information is used to establish decision support systems, which enable an entirely holistic factory planning. The advantages of the approach are demonstrated by a process chain formation use case.

Abstract: Computational simulations are used for the optimization of production processes in order to significantly reduce the need for costly experimental optimization approaches. Yet individual simulations can rarely describe more than a single production step. Hence, a set of simulations has to be used to simulate a contiguous representation of a complete production process. Besides, sim­ulated results have to be analyzed by domain experts to gather insight from the performed computa­tions. In this paper, an IT-infrastructure is proposed that aims at a rather non-intrusive way of inter­connecting simulations and domain expert’s knowledge to facilitate the collaborative setup, execu­tion and analysis of distributed simulation chains.