Deep learning technologies at embedded world

Furthermore, MVTec will be demonstrating which comprehensive deep learning technologies can be used in embedded vision systems. Visitors to the booth will also find out why investing in professional machine vision software pays off.

Live demos, such as a multi-platform setup, will provide insights into practical applications. In the multi-platform demonstration, four embedded boards will perform different tasks using HALCON and MERLIC. In addition, other platforms that are compatible with the MVTec software will be showcased offline.

The company will also present the HPeek benchmarking demo program using a Raspberry Pi. In another demo, MVTec will present four standard examples of deep learning machine vision technologies in parallel: semantic segmentation, object detection, classification, and optical character recognition (OCR). The performing platform will be an NVIDIA Xavier. A final demonstration will cover the ways in which MERLIC can be used to detect and inspect different objects based on the example of medical test tubes.

MVTec will also participate in the embedded world Conference, which takes place concurrently with the trade fair under the motto ‘Embedded Intelligence’. On February 26th from 2:30 to 3:00pm, Christoph Wagner, Product Manager for Embedded Vision, will hold a presentation entitled ‘Deep learning versus rule-based-configurable vision software on embedded devices’.

In addition, MVTec will contribute to the embedded world Exhibitors’ Forum with a presentation entitled ‘Using MVTec software to combine deep learning and rule-based algorithms to build powerful embedded vision applications’.