FEATURE ARTIFICIAL INTELLIGENCE
AI THINGS HAVE SMALL BEGINNINGS Computer-on-modules for AI-based industrial vision systems
As vision technology, centered around artificial intelligence, becomes a greater focus in automotive applications, Zelijko Loncaric, marketing engineer at Congatec, examines developments in computer-on-modules (COMs) and how these affect AI vision applications going forward
V
ision and artificial intelligence (AI) are megatrends in automation.
Therefore, embedded computer technologies for such systems have to meet increasingly complex demands. What’s good enough for today may be too little tomorrow, in terms of processor performance or the number of onboard interfaces. With their high scalability, computer-on-modules (COMs) can provide the necessary flexibility and, as convergent components, are even suitable for closed-loop engineering of automation systems. It becomes obvious that AI based vision technology holds a dynamic future when one looks at one particular sector: the camera technology market for autonomous robotic vehicles. Due to extensive market growth, there is an increased demand for camera installation. But with this comes the concern of image data and how it will be processed. Cameras with higher resolutions promise safer situational awareness. But this adds weight to the work done by subsystems for data preprocessing, embedded computing cores and their GPGPUs. This trend also affects industrial autonomous vehicles, as well as collaborative or cooperative stationary robotics and all other industrial vision systems.
HOW THE COMMERCIAL SECTOR INFLUENCES INDUSTRY According to Yole Développement, the camera technology market for industrial vision systems will be 50 per cent larger than the camera technology market for autonomous robotic vehicles. However, the strong growth in revenue for cameras in autonomous robotic vehicles will also affect the market for industrial vision systems: AI is crucial for vehicles and the experience gained here is, in basic technology terms, transferrable to industrial robotics. Therefore, both application areas will develop very dynamically. This leads to the demand for more effective COMs to cope with the demands of the camera technology market.
SCALABLE PERFORMANCE FOR A DYNAMIC ENVIRONMENT Highly dynamic, AI-focused markets, such as the ones mentioned earlier, require embedded computer technologies with flexible scalability. This is often referred to as closed-loop engineering, based on complementary hardware platforms. The goal is to implement ongoing optimisations in a closed loop, analysed in digital twins, based on the large amount of data generated by IoT connected AI systems.
COMs are the perfect basis for scaling
the embedded computing core. They are standardised, come in various form factors such as COM Express, SMARC 2.0 and Qseven, and can support a broad range of processors in different performance classes. COM Express leads the current high- end class of modules. Offered with Intel Core and Xeon processors, they are scalable to the AMD G-Series or entry-level systems such as Intel Pentium, Celeron and Atom. SMARC 2.0 and Qseven alternatively cover the lower range of low-power embedded computing, with smaller dimensions.
Computer-on-Modules such as SMARC and Qseven are designed for closed-loop engineering, based on convergent computing cores
SPOILT FOR CHOICE
The market for autonomous robotic vehicles is growing rapidly, as is the market for industrial vision systems, connected through their embedded artificial intelligence
Congatec, for example, offers two brand new processors from the NXP
i.MX 8 series, on SMARC 2.0 and Qseven modules. While both target the automotive sector, they are also applicable to industrial automative AI applications. The NXP
i.MX 8 QuadMax supports 2 MIPI-CSI interfaces, while the new
i.MX 8X targets particularly energy- efficient systems with a somewhat reduced feature set. Intel Atom, Celeron and Pentium processors are available on SMARC 2.0 as well. But more relevantly, they can directly access MIPI-CSI interfaces, as Congatec’s MIPI-CSI 2 Smart Camera Kit for vision systems demonstrates. This assists with the deployment of MIPI-CSI 2 based smart camera analytics in autonomous vehicles, for harsh industrial, outdoor and automotive circumstances. This shortens the time- to-market, enabling quicker decision making on which processor platform would best suit the technical design.
Congatec
www.congatec.com Tel: +49 (991) 2700-0
36
MAY 2019 | ELECTRONICS
/ ELECTRONICS
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
