fpga Related Articles

To help detect and prevent possible incidents at critical facilities and public venues, Intel technology is powering a face recognition engine that can rapidly and accurately identify people, even when they are moving and in a crowd. NEC relied on Intel Arria 10 field programmable gate arrays (FPGAs) operating on Intel Xeon processor–based servers to increase the performance of its NEC NeoFace facial recognition engine to a level where an individual can be identified smoothly from a high-resolution image with dozens of faces.  “Facial recognition in a moving crowd requires highly advanced techniques when compared to still images because these cameras are affected by many factors: camera location, image quality and lighting, along with the subject’s size, walking speed and face direction,” said Tadashige Kadoi, general manager of IoT Platform Development Division, NEC. “Intel FPGAs and their parallel processing capability help NEC to enable fast and accurate collection and processing of images from even 4K high-resolution remote cameras.” Intel FPGA acceleration technology played a role in a recent achievement for NEC. In March, NEC NeoFace was ranked Number 1 in almost all tests by the US National Institute of Standards and Technology (NIST) specifically for face-in-video evaluation. The NIST tests evaluated the accuracy of the technology in two real-life test scenarios including a test for entry-exit management at an airport passenger gate. It determined whether and how well the engine could recognise people as they walked through an area one at a time without stopping or looking at the camera. NEC's face recognition technology won first place with a matching accuracy of 99.2%. The error rate of 0.8% is less than one-fourth of the second place error rate. In the second test, the technology was asked to detect suspicious individuals at an indoor stadium. This test was conducted with an individual situated far from the camera, with their face direction changing frequently. NEC's face recognition technology won first place with an error rate half that of the second place error rate. To create the NeoFace Accelerator, NEC’s NeoFace facial recognition engine software IP is integrated into an Intel Arria 10 FPGA, keeping the same accuracy level while achieving higher performance in facial recognition than the previous solution. Intel teams also worked with NEC to enhance the performance of NeoFace data centre server technology. NEC NeoFace Accelerator includes not only the Intel Arria 10 FPGA, but also an Intel MAX 10 low-cost FPGA and Intel Enpirion power devices. Ref.KY32-EP1S60B956C6KY32-EP4CGX150DF27I7 

A software called DesignDRIVE Fast Current Loop that makes C2000 microcontrollers (MCUs) the first devices to push current-loop performance to less than 1 microsecond, has been introduced by Texas Instruments. Together, TI's C2000 MCU portfolio and DesignDRIVE software delivers System-on-Chip (SOC) functionality which simplifies drive control system development.       The DesignDRIVE Fast Current Loop software out performs traditional microcontroller (MCU)-based current-loop solutions and can simplify designs by eliminating the Field-Programmable Gate Array (FPGA) typically used for external current-loop control. Fast Current Loop software is a free update available for C2000 controlSUITE software.   TI's DesignDRIVE technology is a unified hardware and software platform that makes it easier for engineers to develop and evaluate solutions for a variety of industrial drive and servo topologies. As a key part of DesignDRIVE solutions, the Fast Current Loop software enables developers to achieve higher control performance while saving valuable board space and simplifying thermal considerations.     Features and benefits of TI's DesignDRIVE Fast Current Loop software   · Innovative subcycle Pulse-Width Modulation (PWM) update techniques significantly improve control-loop bandwidths to potentially triple the motor torque response. · A novel cycle-scavenging C2000 MCU needs only 460 nanoseconds for field-oriented control processing. · A new complex controller replaces traditional proportional integration control and facilitates greater stability at higher speeds. · Industrial drive systems designed with Fast Current Loop software on a C2000 MCU, like the TMS320F28379, delivers SOC functionality to reduce board space, complexity and overall cost.      Ref. KY32-TMS320F28379 KY362-C2000    

The introduction of the LDD-ES8, a customisable gigabit Ethernet switch module for industrial, commercial and building automation data services, has been announced by LDD Technology. The standard LDD-ES8 module is an 8 port unmanaged Ethernet Switch on a PC/104-Plus form factor intended for use in embedded applications. It features a high performance, low latency, switch able to handle full-rate gigabit packets on all ports simultaneously.Auto-negotiation allows each port to operate at 10/100/1000 Mbits with dual LEDs per port to indicate negotiated speed and link activity. Power is provided from the PC/104 stack or through a Molex Microclasp connector. The LDD-ES8 module is designed for fully independent operation but a USB port is provided to allow monitoring of port performance if required. Power consumption is typically 5W with all ports operating at 1 Gbit/sec.The LDD-ES8 Gigabit Ethernet switch was developed in response to a number of enquiries for custom designed products from customers who had been unable to find suitable off-the-shelf products which met their performance, footprint and end product life requirements.LDD Technology is able to offer an efficient and cost-effective customisation service in the event that customers require a design with a different number of ports or in a different form factor. The module has been designed using programmable FPGA technology which offers end users a further range of customisation options not normally found on competitive products based on dedicated devices with limited programmability.This allows customers the option of including the functionality of the standard Ethernet Switch into other designs which may require Ethernet switching as part of a more complex system with additional interfaces or processing being included in the FPGA as required.“Our LDD-ES8 Gigabit Ethernet Switch is an excellent example of how our extensive custom design experience for many different clients can be used to create a flexible standard solution for many applications” commented Malcolm Locke, Managing Director of LDD Technology. Ref:KY32-EP1S60B956C6KY32-XC7K325T-2FFG900CKY32-EPF8636ALC84-3

Lattice Semiconductor has introduced its first embedded vision development kit for mobile designs that require low power image processing.  The low power processing comes from the firm’s ECP5 FPGA, which is combined with an HDMI chip and CrossLink pASSP mobile bridging device.According to Lattice product marketing director, Deepak Boppana, the low power  mobile applications include machine vision, smart surveillance cameras, robotics, AR/VR, drones and Advanced Driver Assistance Systems (ADAS).The CrossLink input board includes dual-camera HD image sensors supporting the MIPI CSI-2 interface, eliminating the need for external video sources.The ECP5 base board enables low-power pre/post processing and includes support for HD image signal processing IP from Helion Vision.Also included is a NanoVesta connector to support external image sensor video inputs. The HDMI output board based on the Sil1136 non-HDCP version enables connectivity to standard HDMI displays.Ref:KY32-LFSCM3GA25EP1-6F900CKY32-ICE65L04F-TCS63I