SoM powers AI-enabled cameras

A system on module (SoM) by Smart Wireless Computing, the Inforce 6403, is based on Qualcomm’s QCS610. It enables advanced visual computing for AI-enabled surveillance camera and edge appliances, connected body cameras, smart displays, and other IoT wireless network edge devices, says the company. 

Engineers can use the Inforce 6403 SoM to bring on-device AI and machine learning (ML) to cameras and displays, while enabling multiple connectivity options for critical data transfer. 

It supports 4K UltraHD (HEVC) video capture and playback to enable video analytics applications integrated into smart cameras, such as face detection and object tracking. High-bandwidth connectivity options include Ethernet RGMIII, 802.11nac Wi-Fi, Bluetooth 5.x, USB-C, and LTE Cat 4 via a carrier board.

The compact LGA package measures just 43 x 32.5mm (1.69 x 1.28 inches), allowing it to integrate into camera housings and systems, particularly in applications where a soldered connection is required for a rugged end-product.

The module comes with a software package that includes integration with Google Firebase and a sample application to upload or stream videos in real time. Google Firebase is a unified backend-as-a-service (BaaS) platform for mobile and web developers that integrates with other Google services.

The Qualcomm QCS610 SoC integrates a Qualcomm Kryo 460 CPU with independent efficiency and power clusters. There are also dual 14-bit Qualcomm Spectra 230 image signal processors which support up to 24Mpixels for simultaneous concurrent cameras capturing sharp images.

The Qualcomm Adreno 612 GPU provides efficient rendering of advanced 3D graphics.

The SoC also leverages Qualcomm Hexagon Vector eXtensions (HVX) on Hexagon 685 DSP enable accelerated machine learning through deep neural network models and with advanced Qualcomm neural processing engine SDK support and TensorFlow Lite.

A secure processing unit enables secure boot, DRM and content protection for a secure environment for the camera system.

The Inforce 6403 SoM incorporates enhanced EMI shielding for RF noise protection, while also improving heat dissipation to improve performance.

A reference design based on the SoM is available.

https://www.inforcecomputing.com

> Read More

IAR Embedded Workbench supports Arm Cortex-55 core for AI

Support for the latest Arm Cortex-M55 processor has been announced by IAR Systems. The latest version of IAR Embedded Workbench for Arm adds support for the Arm Cortex-M55 processor. In addition, version 9.20 of the toolchain includes support for latest microcontroller devices from several semiconductor vendors.

The Arm Cortex-M55 processor is Arm’s AI-capable Cortex-M processor and the first to feature Arm Helium technology, M-Profile Vector Extension (MVE). It is characterised by energy-efficient digital signal processing (DSP) and machine learning (ML) capabilities. The IAR Embedded Workbench for Arm toolchain delivers powerful optimisation capabilities to assist developers in getting the most out of the performance of the microcontroller while maintaining energy efficiency. To ensure code quality, code analysis tools are completely integrated with IAR Embedded Workbench.

The support for Cortex-M55 is intended to help early development based on the core in the ecosystem. 

In a simultaneous announcement, the company announced that the latest IAR Build Tools for Arm provides support for Linux and Windows installations, which enables implementation in cross platform-based frameworks and large-scale deployments of critical software building and testing. 

IAR Systems says it supplies future-proof software tools and services for embedded development, enabling companies worldwide to create the products of today and the innovations of tomorrow. Since 1983, IAR Systems’ solutions have been used in the development of over one million embedded applications. 

The company is headquartered in Uppsala, Sweden and has sales and support offices all over the world. In 2018, Secure Thingz, the global domain expert in device security, embedded systems, and lifecycle management, became part of IAR Systems Group AB. 

http://www.iar.com

> Read More

Jetsys-5320 meets data processing rates for AI, says Elma 

Based on Nvidia’s GPU processing, the Jetsys-5320 enhances inference computing in data driven embedded systems, says Elma Electronic. It provides general purpose GPU inference computing at the edge for deep learning and machine learning operations in AI applications.

It combines the Nvidia-based computation with a rugged, low power computing systems for intelligent video analytics (IVA), virtual reality (VR), augmented reality (AR) and AI at the edge, as well as in unmanned or autonomous vehicles and robots.

According to Elma, it increases visual intelligence throughout transportation and defence applications including high resolution sensor systems, movement tracking security systems, automatic target recognition, threat location detection and prediction as well as machine condition-based monitoring and predictive maintenance, semi-autonomous driving and driver advisory systems.

The JetSys-5320 is based on the Nvidia Jetson TX2i system on module (SoM). Using a dual-core Denver 2 64-bit CPU and quad-core Arm A57 Complex and 256 CUDA cores, Nvidia’s Pascal architecture delivers 1.3TFLOP performance. 

The system also provides HD-SDI, Gigabit Ethernet with PoE, USB 3.0 interfaces for video capture and miniPCIe expansion slots. The JetSys-5320 operates in temperatures from -40 to +71 degrees C, offers IP 67-rated ingress protection and meets MIL-STD-810G for harsh environments.

“AI-based computing is enabling multiple levels of intelligence and safety advancements throughout the embedded computing industry,” said Ram Rajan, vice president of engineering at Elma Electronic. “We’re seeing a huge increase in object detection and tracking, video surveillance, target recognition and condition-based monitoring, so we built an AI platform that could handle the processing requirements for these kinds of applications used in challenging environments.” 

Elma’s other SFF modular embedded computing systems include the ComSys family for communication-based computing and NetSys series for networking applications

Elma Electronic manufactures commercial, industrial and rugged electronic products for embedded systems and application-ready platforms – from components, embedded boards, backplanes, chassis and enclosures, power supplies, to fully integrated subsystems. 

It also offers standard and custom cabinets and enclosures as well as precision components such as rotary switches/encoders, LEDs, front panels and small cases.

The company leverages proven technology based on VITA, PICMG, and other standards-based architectures (i.e. OpenVPX, SOSA, VME, CompactPCI Serial, COM Express and PCIe/104). Elma is also actively engaged in designing solutions for applications requiring smaller footprints. 

http://www.elma.com

> Read More

COM Express Type 10 mini module supports up to four cores

Based on the Intel Atom x6000E series processor (Elkhart Lake), the PCOM-BA02VGL is a COM Express Type 10 mini module by Portwell. It features an operating temperature range of -40 to +85 degrees C. 

The PCOM-BA02GL measures 84 x 55mm and is based on the 10nm Intel Atom x6000E series / Pentium / Celeron processors (formerly Elkhart Lake). It supports up to four cores with 4.5 to 12W TDP (thermal dynamic performance) and integrates the Intel Gen 11 UHD graphics engine with triple displays support in 4K resolution. 

The PCOM-BA02GL COM Express module includes optional I/O flexibility, for example Gen 3 PCI-Express and is designed to enable applications using Type 10 COM Express products to rapidly upgrade systems without changing carrier boards or an entire computer system. It also minimises changes in software, says Portwell.

The PCOM-BA02GL COM Express module supports up to 8Gbyte LPDDR4 3200M transfers per second SDRAM soldered onboard memory with integrated in-band ECC which allows more affordable standard memory to be used instead of more expensive ECC memory (ECC or non-ECC can be configured by BIOS), explains Portwell. The module can support up to 3.0GHz in turbo mode, increasing cost-performance effectiveness, adds the company. There are also two USB 3.2 Gen 2 (10Gbits per second), 2.5GbE LAN with the support of Intel TSN (time sensitive networking) and time co-ordinated computing (TCC) for real-time computing and control with low-latency capability. There are also four PCI Express x1 Gen 3 (8.0Gtransfers per second) expansion interfaces. According to Sid Huang, Portwell’s product manager, this is the first time PCIe Gen 3 is available in the lower power processors, ensuring the modules can fulfil most applications that need great expandability and higher throughput such as Wi-Fi, Bluetooth and NVMe modules. The PCOM-BA02GL COM Express module also supports dual 4K high resolution display including DP/HDMI and LVDS/ eDP that delivers up to two times faster graphics performance compared to the previous generation. 

The low power Intel Atom processor x6000E family is housed on the PCOM-BA02GL module board. In this design, Huang explains, the company has maximises COM technology to produce a unit that not outputs under 4.5 to around 12W for fanless applications, but which also supports a wide industrial temperature range and wide voltage input (4.75 to 20V DC). The module conserves energy resources, minimises carbon impact and keeps energy budgets under control, he added.

The compact and rugged PCOM-BA02GL is suitable for mission critical applications in harsh environments, and applications such as industrial automation, factory automation, process control, embedded system for IIoT, edge computing, manufacturing, intelligent gateway, transportation. 

http://www.portwell.eu

> 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