Smart Cities

Video decoding, pre-processing, artificial intelligence (AI) inference, tracking and post-processing are enabled with the latest Vitis Video Analytics software development kit (SDK), announced by Xilinx.

It is a complete software stack for intelligent video analytics applications on Xilinx platforms, deployed edge-to-cloud. The end-to-end video analytics supports widely used AI models such as YOLO, SSD, ResNet, Inception, RefindDet, ReID, FPN and OpenPose for real-time objection detection, classification and segmentation.

The software development kit provides the foundational layer for video analytic applications such as understanding vehicle and pedestrian traffic patterns in smart cities, health and safety monitoring in hospitals, self-checkout and analytics in retail, and detecting component defects at manufacturing facilities.

In provides a complete framework for developers to create generic infrastructure plugins, software acceleration libraries, and an interface to develop a custom acceleration library to control a custom hardware accelerator. The SDK builds on top of and abstracts the complex interfaces of Xilinx Run Time (XRT) and Vitis AI tools, making it easy for developers to build video analytics and transcoding pipelines without having to learn the complexities of XRT and Vitis AI tools.

To meet the evolving requirements and demands of video and vision applications such as smart cameras, industrial vision systems, automotive driver assistance and autonomous driving, smart retail and security, broadcast, professional AV and consumer products like TV and gaming applications, Xilinx says it has expanded its video and imaging IP portfolio for UltraScale+ and Versal devices.

The company enables 8K video capture and 8K display with what is believed to be the industry’s first HDMI 2.1 and DisplayPort (DP) 1.4 with UltraScale+ and Versal products. Combining HDMI 2.1 or DP 1.4 with the 8K scaler and mixer IP allows customers to build an end-to-end 8K video pipeline. For immersive gaming experiences, Xilinx’s video and imaging portfolio now includes high dynamic range (HDR), high frame rates and variable refresh rate formats and adaptive sync across the UltraScale+ and Versal families.

Xilinx has also added capabilities in the video IP, including 4k60 Warp with horizontal and vertical keystone correction, lens distortion correction, rotation and arbitrary warp for video walls, advanced conferencing cameras, projectors and applications in automotive.

There are also further Vitis Vision libraries for developers across automotive, industrial machine vision and smart camera applications, which includes image signal processing (ISP) with HDR and pre- and post-processing functions for machine learning (ML) neural networks with the OpenCV API.

The company has also announced the Vivado release 2021.2 will support 4:4:4 YUV colour space within the Xilinx Zynq UltraScale+ EV family. It is expected to be released by end of year.

http://www.xilinx.com

Equipped with the 11th generation Intel Core U processors, the PICO-TGU4 is the latest PICO-ITX board from Aaeon. It is intended for industrial artificial intelligence (AI) and machine vision applications.

The 11th generation Intel Core processors (formerly Tiger Lake) are based on Intel’s 10nm microarchitecture, delivering up to 15 to 20 per cent better performance than the previous generation processors. The PICO-TGU4 is available with Intel Core U i3 / i5 / i7 or Intel Celeron processors. All of these processors support data integrity, accuracy and security, including on-board TPM 2.0 and in-band memory error code correction (ECC) with selected models. There is also up to 32Gbyte of on-board LPDDR4x memory, making the PICO-TGU4 capable of deployment in a wide range of embedded and edge computing applications, said Aaeon.

The PICO-TGU4 has two expansion slots which can be used to add functionality to power AI edge applications. The M.2 2280 slot delivers PCIe 4.0 [x4] speeds, for AI accelerator cards such as the AI Core XM2280, as well as providing the throughput needed to support the next generation of AI accelerators. The full-sized Mini Card (mPCIe) slot has support for AI accelerators, wireless modules such as Wi-Fi or LTE, expanded storage with mSATA support and 30-bit digital I/O cards.

The PICO-TGU4 offers a broad I/O layout allowing the board to easily connect to a wide range of sensors and devices or integrate with projects. There are eight USB connections, made up of two USB3.2 Gen 2 type A ports, two USB3.2 Gen 1 headers and four USB2.0 headers. There are also two serial port headers and 8-bit GPIO and I2C/SMBUS connectors.

The PICO-TGU4 also features dual LAN ports, one Intel i225 2.5Gbits per second port for fast LAN connectivity and an Intel i219 port with support for Intel vPro, enabling remote system monitoring. Storage includes both SATA III (6.0Gbits per second) and support for Mini Card mSATA storage. Additionally, there are eDP and HDMI 2.0 ports for 4K 60Hz resolution.

The PICO-TGU4 is backed by Aaeon’s expertise in building compact, rugged solutions to operate in a wide range of industrial and other environments. Aaeon also offers a range of manufacturer and OEM/ODM services, from customising board layouts to helping developers create a board level solution that fits application requirements.

Established in 1992, Aaeon designs and manufactures industrial IoT and AI edge  computing platforms including industrial motherboards and systems, rugged tablets, embedded AI edge systems, uCPE network appliances, and LoRaWAN / WWAN.

The company is an Associate member of the Intel Internet of Things Solutions Alliance.

http://www.aaeon.com