Embedded Technology
congatec, Basler and NXP present retail deep learning application
The goal: Fully automated checkout A
t Embedded World 2019, congatec, Basler and NXP Semiconductors presented a retail deep learning
application at their respective booths. The platform is a proof-of-concept utilising Artificial Intelligence (AI) to fully automate the retail checkout process. It was created by Basler and is being supported by the close partnership with congatec and NXP. This solution shows the possibilities of vision for embedded applications and how they can simplify our everyday life. Booth visitors selected what to put in their baskets, and the trained neural network then detected the products on the basis of a video stream – similar to how face recognition works – and finally the total pricing was displayed. Systems like this open new perspective for retail applications: It makes it easy to add new products to the sales portfolio as products can easily be added to a trained neural
network. Retail stores benefit from less labour costs as well as significantly improved customer experience through instant checkouts, minimised queues and 100 per cent checkout capacity at all times, even when the shop is opened 24/7. Ron Martine, vice president for
i.MX applications processors at NXP Semiconductors, explains the benefits of the
i.MX 8 family in this application. “Our recently launched NXP
i.MX 8 applications processors are perfect candidates for these high volume applications as they support up to 2 MIPI cameras natively with a TDP of only a few watts, integrate support for neural networks as well as up to four Full HD displays, and feature safe domain separation, e.g. to securely separate payment and scanning. They offer all embedded processing capabilities required to build entire self-checkout systems based on a single silicon platform.”
Martin Danzer, director of product management at congatec, highlights how congatec supports the platform in this retail application setup: “We offer these impressive
i.MX 8 applications processors to customers as an application-ready embedded hardware platform on the basis of commercial off- the-shelf available Computer-on- Modules. Moreover, for large scales of self-checkout systems we supply a full service on demand, from designing customised carrier boards to cost efficiently merging modules and carrier logic in a full custom design. In a first step, customers can test the various performance variants of the BGA processors by simply switching the modules on our evaluation carrier boards as required. As a next step, we deliver the tailored embedded computing platform in a cost and space-optimised full custom design.” Gerrit Fischer, head of product market management at Basler, is happy to have such strong partners for its embedded vision solutions: “This Retail Deep
Learning Application is based on our new Embedded Vision Kit and shows how the strategic partnerships with congatec and NXP support us in building the best embedded vision solutions for our customers. With Basler Embedded Vision becomes easy: Be it with our easy-to- integrate Embedded Vision Kits that offer an excellence base for solutions in many different fields our with our services that support you on the whole way from the product idea to the final solution.” The Retail Deep Learning Application shown at the embedded world booths of congatec (hall 1, stand 358), Basler (hall 2, stand 550) and NXP Semiconductors (hall 4A, stand 220) was based on a Basler Embedded Vision Kit consisting of an NXP
i.MX 8QuadMax SoC mounted on the conga-SMX8 SMARC 2.0 Computer-on-Module from congatec, a SMARC 2.0 carrier board and Basler’s dart BCON for MIPI 13 MP camera module. The Embedded Vision Kit will be available starting this summer from Basler.
www.congatec.de
14 March 2019
Components in Electronics
www.cieonline.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
