Research Group Efficient Embedded Systems THA-Logo
TH Augsburg / Faculty of Computer Science / Research Group EES german
Home
Team
Job vacancies
Open
degree theses
Lab
Research
PicoNut
THANNA
ParaNut
ASTERICS
ChASA
Triokulus
e4rat
HiCoVec
Teaching
Publications
Imprint

ChASA

CAD model-based, hardware-supported measurement
for ship and plant building processes

Logo_BMWi

The ChASA project is a research project funded by the Federal Ministry for Economic Affairs and Energy (BMWi). It deals with the development of a mobile device to measure the as-is state in plant building processes. Computationally intensive algorithms are to be accelerated by hardware structures realized within an FPGA. The project will be carried out in close cooperation with industry and other research institutions.

In the field of plant construction, it is customary to record the current status of work on the site at regular intervals. This is necessary as a result of unforeseeable problems while parts of the site are not implemented as planned. However, following work process steps require current plan data, such as for connecting points of aggregates. Traditionally, these are determined by a complex, manual measurement. The timely close and efficient refeeding of 3D raw data into the planning system is - in addition to the high investment costs - still an unsolved problem. In order to reduce cost and deployment time this project aims to develop a low-cost mobile solution to address this problem. The status of the work process is to be determined on the site in a short time and refeeded to the planning system. A key innovation is the measurement by low-cost, mobile 3D sensor technology, the use of FPGA-accelerated computer vision algorithms and a model-based scene interpretation.

As a mobile device with limited computing power is to be used, an efficient implementation of the algorithms is required. FPGAs provide the flexibility needed to develop hardware structures that can be optimally adapted to a given algorithm and exploit the parallelization efficiently. The research group "Efficient Embedded Systems" deals with the development of complex and efficient hardware structures for the involved geometry and feature extraction steps in this project.

Project Partners

17.4.2024 - Michael Schäferling - Technische Hochschule Augsburg