Research & Innovation

No limits

Researchers at Chemnitz University of Technology are at CeBIT 2016 in Hannover with software for developing image processing systems – breaking down barriers in terms of both operating systems and computer architecture.

03 Mär. 2016
tu_chemnitz_xpcv

From robotics to semi-autonomous driving and smart home applications, machine vision plays a key role in the development of the Internet of Things. Although increasingly powerful, energy-efficient and cost-effective processors offer great opportunities to compensate for the limited performance and energy resources of mobile and integrated computer systems, developers still have to spend a lot of time, effort and money developing tailor-made solutions for each task. However, researchers at Chemnitz University of Technology (TU Chemnitz) are hoping to change all that. The Saxony-based research team is exhibiting the Cross-Platform Computer Vision (XPCV) framework at CeBIT 2016 to show how image processing systems of the future could be developed across the boundaries of operating systems and computer architecture.

With a modular approach to developing image processing systems, XPCV significantly reduces the complex development processes required for communication protocols and hardware-optimized algorithms. TU Chemnitz researcher Lars Meinel explains: "Thanks to an intuitive graphical user interface and an ever-expanding library of modules, even inexperienced developers can work with single-board computers such as Raspberry Pi to create functional image processing systems. Meanwhile, for more experienced developers, benefits include improved configurability, parameterization and processing chain testability." The end results are reduced development costs and faster time to market for image processing systems, which means that applications for smart homes and other price-conscious markets are a real possibility.

Chemnitz University of Technology (09111 Chemnitz, Germany), Hall 6, Stand B24

Research & Innovation Internet of Things CEBIT RSS Feed