Subaru bases enhanced EyeSight system on Xilinx Zynq

Xilinx’s automotive-qualified (XA) Zynq UltraScale+ multi-processor SoC (MPSoC) has been selected by Subaru for its next generation EyeSight system as part of its advanced driver assistance system (ADAS) in its latest model which has been launched in Japan this week.

The Levorq model’s EyeSight system is vision-based, using stereoscopic cameras and will provide advanced features including adaptive cruise control, lane-keep assist and pre-collision braking, says Xilinx.

The vision system is based on Xilinx’s 16nm XA Zynq UltraScale+ MPSoC which provides the high-performance, low latency, and functional safety (ASIL) capabilities that the EyeSight system requires to accurately depict and react to dynamic driving scenarios.

Tetsuo Fujinuki, chief technology officer of Subaru said: “Stereo cameras are at the heart of Subaru’s ADAS applications. Unlike common approaches, the image processing technology adopted in our new generation system scans everything captured by stereo cameras and creates high-precision 3D point clouds, enabling us to offer advanced features such as pre-collision braking at an intersection and assisting with hands-off driving in traffic congestion on a highway. Xilinx technology plays an important role in this. Because Xilinx automotive devices contain built-in capabilities that allow us to meet strict ASIL requirements, they are unquestionably the best technology to implement Subaru’s new ADAS vision system.”

Programmable logic provider, Xilinx has over 20 years of automotive industry experience, offering hardware and software partitioning flexibility combined with a variety of networking connectivity options, functional safety architecture configurations, and security features for current and future autonomous drive modules.

Xilinx says it has shipped over 190 million devices globally for automotive use, with 75 million used for production ADAS deployments. It works with over 200 automotive companies, comprised of major Tier 1s, OEMs, and start ups around the world.

California-based Xilinx develops adaptive processing platforms for a variety of technologies, from the endpoint to the edge to the cloud. Xilinx is the inventor of the FPGA, hardware programmable SoCs, and the ACAP.

http://www.xilinx.com

> Read More

Single chip physical layer interface devices are based on CoaXPress 2.0

Accelerating machine vision image capture while also contributing to the simplifying of system design and deployment, Microchip Technology’s EQCO125X40 family of CoaXPress devices is believed to be the first to implement the CXP 2.0 standard.

The single chip, physical layer interface devices can be used to create capture cards and cameras supporting the new specifications.  The 12.5Gbits per second CoaXPress 2.0 interface standard was ratified last year. It addresses machine-vision image-capture to accelerate production-line throughput. Microchip says it has taken the next step, after ratification, towards realising the full potential of CoaXPress (CXP) on the factory floor. These single chip, physical layer interface devices include features that streamline machine vision system design, maximise transmission speed and simplify deployment in high-volume industrial inspection and imaging applications.

The company has worked with the Japan Industrial Imaging Association (JIIA) standards organisation and lead customers to optimise the EQCO125X40 family of CoaXPress devices and to fully exploit the specification’s benefits on the factory floor.

“Our low-latency, low-power transmission solutions integrate an equaliser, cable driver and clock data recovery into a single chip that enables camera and capture card manufacturers to deliver high-speed, high-resolution video and control signaling along with power over a single coax cable,” explains Matthias Kaestner, vice president, Automotive Infotainment Systems business unit.

Microchip’s EQCO125X40 family of CoaXPress devices is claimed to be the first to implement the CXP 2.0 standard, starting from a new backwards-compatible design based on the specification. They have an integrated clock data recovery (CDR) at all speed levels and a camera-side clock to support the demands of real-world environments.

The devices significantly increase machine-vision processing throughput by enabling cameras and capture cards to transmit four to eight times faster than alternative solutions, reports Microchip. In addition, the EQCO125X40 CoaXPress devices enable four times the cable/link distance with much lower power and near-zero latency, Microchip says.

The family also increases design tolerances and flexibility by seamlessly locking on all frequencies at any speed, from CXP-1 to CXP-12, and eliminates the need for multiple channels by supporting 12.5Gbits per second of bandwidth over a single cable. Broader cabling options ensure systems can be installed where needed and the integrated CDR improves jitter performance for the signal sent from the camera to the capture card.

The on-camera low-frequency clock recovery eliminates the need to program a separate clock in the FPGA. The integrated link signal integrity testing enables the system to perform real-time checks of cable link integrity before and during operations.

They also enable pre-setup and real-time cable link quality tests to be performed, and also have the option to scale up to 50Gbits per second over multiple cables.

According to Microchip, the CXP devices enable manufacturers to get the same throughput from two ports on cameras and frame grabbers as they previously could with four. The devices can be used to retrieve a real-time low-frequency clock at the camera side, which provides more accurate signal timing. The manufacturers can also use it as a cable repeater, further extending the distances over which the cameras can be linked. Their low power consumption makes them suitable for developing smaller, better-performing image-capture solutions that are simpler and less costly to design.

The CoaXPress 2.0 family is also suitable for use in traffic monitoring, surveillance and security, medical inspection systems and embedded vision solutions.

The Microchip CoaXPress 2.0 family includes a transmitter-only camera-side device and three single-chip transceiver options. Each is packaged in a 16-pin quad-flat no-leads package and is fully backwards-compatible with Microchip’s CoaXPress 1.1 family of devices.

http://www.microchip.com

> Read More

Blaize builds embedded and accelerator platforms using its GSP architecture

Efficient and cost-effective real-time AI computing is the promise of the Blaize Pathfinder and Xplorer platforms by Blaize. The embedded and accelerator platforms are built on the Blaize Graph Streaming Processor (GSP) architecture, designed for the demands of real-time AI edge computing.

The Pathfinder and Xplorer platforms coupled with the Blaize AI software suite are claimed to enable developers to introduced commercially viable edge AI products across a wide range of edge use cases and industries.

 According to Dinakar Munagala, co-founder and CEO, Blaize, the AI edge computing products overcome “limitations of power, complexity and cost to unleash the adoption of AI at the edge, facilitating the migration of AI computing out of the data centre to the edge”.

The GSP provides 16 GSP cores and 16TOPS of AI inference performance within a tiny 7W power envelope and is claimed to deliver up to 60x better system level efficiency compared with GPU/CPUs for edge AI applications. It also enables 50x less memory bandwidth and 10x lower latency without compromising flexibility, says the company. The programmable processor’s capabilities include multi-threading and streaming.

The Pathfinder P1600 embedded system on module (SoM) brings the programmability and efficiency benefits of the GSP to embedded edge AI applications deployed at the sensor edge, or on the network edge. No host processor is needed for the P1600.

The Blaize Xplorer Accelerator platforms are built to accelerate AI applications at the edge of the enterprise, via plug-in, to the PCIe slot in a host server or appliance. The X1600E is a small form factor accelerator platform for small and power-constrained environments such as convenience stores or industrial sites. This accelerator form factor can accelerate AI apps in industrial PCs or as a rack of cards in a small 1U server.

The X1600P is a standard PCIe-based accelerator in a half-height, half-width form factor. It is designed to replace a power-hungry desktop GPU in edge servers and provide between 16 to 64TOPS of AI inference performance within a very low power envelope.

The Blaize AI software suite is built on open standards and comprises the Picasso software development kit (SDK) and AI Studio, a completely code-free visual interface. The software suite offers tools for both traditional developers and non-coder domain experts.Both tools sets use Blaize Netdeploy, which has edge-aware algorithms to get the best accuracy and performance for edge deployments.

Intended applications are in industrial settings, where five independent neural networks can run at 50 frames per second with less than 100ms aggregate latency monitoring human and robot pose detection and position, product ID and count, and product quality.

Another application area is smart cities, where three independent neural networks can monitor human detection, pose, position, auto detection and traffic intersection safety and security.

In the same smart city, high resolution FHD video and lidar/radar sensor fusion can run as a complete graph-native application on Blaize GSP. For example, sensor fusion of HD cameras can run at 30 frames per second combined with lidar/radar with less than 100ms latency and less than 15W power, can be used in last mile delivery.

Another application is in retail where four independent neural networks, also running at 50 frames per second can monitor human detection, position, mask and incidences of theft for store safety and security and product detection.

Customer samples of both Blaize Pathfinder and Xplorer are available now with full production expected starting in Q4 2020.

The Blaize Xplorer X1600E is available for $299 in volume quantity, the Pathfinder P1600 SOM is available in industrial grade for $399 in volume quantity, and the Blaize Xplorer X1600P is available for $999 in volume quantities.

http://www.blaize.com

> Read More

E-paper display provides information in smart cities

Suitable for public information display in connected cities, the EDP-3133 series e-paper display can be used for smart bus stop signs and real-time public transport information systems. When combined with wireless transmission it can be used in offices or venue to replace traditional single-use paper posters and labels.

Manufactured by Avalue Technology in Taiwan, the 31-inch display is available from Display Technology.

It provides 16-level greyscale black and white and a 180 degree viewing angle. The e-paper technology is responsible for the high quality of viewing even under strong light, says Display Technology.  This is also responsible for low power consumption and bistability, retaining a static image even when powered off, says the company.

The EPD-3133 is an open frame embedded design controlled with an Intel Celeron Apollo Lake CPU. This makes it easy to integrate into any public installation, claims the company.

The EPD-3133 is lightweight, slim and easy to install, and there are options to add touchscreen and a front lighting module to assist viewing in low light environments. The display supports LAN, WiFi or LTE allowing the provision for real-time information, delivering warnings, notifications and public announcements remotely.

Avalue provides the link between front end and back end application programming interfaces (APIs) and sample codes. Users may develop programs, organise content and publish processes in accordance with individual needs and makes changes as required.

Users may choose either Windows 10 or Android 8.1.

Established in 1996 as Display Solutions and acquired by Display Technology in September 2018, the UK subsidiary of Fortec Elektronik, delivers the latest technical innovations in displays, touch screens and embedded computing backed by a service ranging from initial consultation through to sample design, volume manufacturing and immediate-response after-sales support.

The company operates within the UK, across all embedded computing market sectors, including industrial instrumentation and control, transportation, retail/point-of-sale, outdoor signage, medical, marine, audio and lighting control and energy management.

http://www.displaytechnology.co.uk

> Read More

About Smart Cities

This news story is brought to you by smartcitieselectronics.com, the specialist site dedicated to delivering information about what’s new in the Smart City Electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: Smart Cities Registration