Week one unveils software developer kit for intelligent video analytics applications, an expanded video and imaging IP portfolio and developer design contest
(Xilinx Adapt) – Xilinx, Inc. (NASDAQ: XLNX), the leader in adaptive computing, today unveiled powerful new solutions and IP for its rapidly growing software, AI, and hardware developer communities at the first week of Xilinx Adapt 2021, the company’s virtual technology conference. Week one is focused on software and hardware developers, with news highlights including a complete software stack for intelligent video analytics applications and an expanded video and imaging IP portfolio for its UltraScale+™ and Versal™ devices.
The company also announced that Hackster.io will again be conducting its Adaptive Computing Challenge design contest with Xilinx. As part of the expanded contest, now in its second year, Hackster.io will award $70,000 USD in total prize money to 15 winners as well as over 350 boards in prizes. The Adaptive Computing Challenge 2021 also adds new categories recognizing innovations by university students and women-in-technology teams. Contest registration opens this week at Adapt.
Taking place September 7-16, Adapt 2021 will feature executive keynotes with appearances from partners and customers, along with a series of more than 100 presentations, forums, product trainings and labs designed to help users unlock the value of adaptive computing. The free, six-day event kicks off this week with three days of content targeting software and hardware developers. The final three days next week will focus on the company’s broad end-market segments, with dedicated sessions covering aerospace and defense, automotive, data center, industrial, medical, and wired and wireless businesses.
“The first week of Xilinx Adapt is designed to educate new, as well as advanced developers on the latest development environments and resources available to more easily build applications on Xilinx® platforms,” said Ramine Roane, vice president of marketing, AI and Software, Xilinx. “We are committed to helping the developer community accelerate applications on adaptive hardware, to propel the industry forward and have a positive impact on people’s lives. We are making programming of adaptive platforms more accessible to all developers, by interfacing to popular domain-specific and more generic open-source development frameworks.”
Adapt 2021 news highlights for week one targeting the developer communities includes the following:
Intelligent Video Analytics Applications
- New Vitis™ Video Analytics SDK, a video analytics software development kit providing a complete software stack for intelligent video analytics applications on Xilinx platforms, deployed edge-to-cloud. The end-to-end video analytics solution enables video decoding, pre-processing, AI inference, tracking and post-processing for whole application acceleration. It supports widely used AI models such as YOLO, SSD, ResNet, Inception, RefindDet, ReID, FPN and OpenPose for real-time objection detection, classification and segmentation.
Vitis Video Analytics SDK 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 addition, it provides a complete framework for developers to create their own innovations with generic infrastructure plugins, software acceleration libraries, and an interface to develop a custom acceleration library to control a custom hardware accelerator. Vitis Video 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.
Expanded Video and Imaging IP Portfolio
Xilinx technology is at the heart of many video and vision applications in the form of smart cameras, next-generation industrial vision, automotive driver assistance and autonomous driving, smart retail and security, broadcast, Pro AV and consumer products like TV and gaming. To meet the evolving requirements and demands of these applications, Xilinx has significantly expanded its video and imaging IP portfolio for UltraScale+™ and Versal™ devices.
- Xilinx is enabling higher-quality 8K video capture and 8K display with 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 its 8K scaler and mixer IPs allows customers to build a complete, end-to-end 8K video pipeline. To provide gamers with immersive gaming experiences, Xilinx 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 product families.
Other advanced new capabilities in the video IP portfolio include 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.
Xilinx is also announcing the availability of comprehensive and improved Vitis Vision libraries used by 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.
Finally, the upcoming Vivado® release 2021.2 will support 4:4:4 YUV color space within the Xilinx® Zynq® UltraScale+ EV family. Combined with Xilinx’s HDMI, DP, video processing and video mixer IPs, and the migration of broadcast and Pro AV to a standards-based approach to transporting AV over IP networks, 4:4:4 color space gives customers the full fidelity of streamed video. Vivado 2021.2 is expected to be released by end of year.
Adaptive Computing Challenge 2021
- Hackster.io is again challenging developers to combine the power of Xilinx adaptive computing platforms with the Vitis unified software platform, Vitis AI development environment or Vivado ML Edition to solve real-world problems. Contestants in the 2021 Adaptive Computing Challenge will compete in three categories: edge computing, data center AI and big data analytics, which includes early access to a new big data analytics developer board for big data and associated applications. Top prize in each category is $10,000 USD.
In addition, the Xilinx University Program is sponsoring Adaptive Computing Challenge submissions from college students for projects in each of the three categories for an additional $2,500 USD prize. The contest is designed to encourage innovation in adaptive compute acceleration at colleges and universities.
Finally, encouraging and celebrating the talents of women is a key initiative for Xilinx. To further support diversity in the technology space, Xilinx is sponsoring a new Women in Technology award with a cash prize of $2,500 USD. Teams composed of at least 50 percent women are eligible to submit their project for this additional award, alongside their edge computing, data center AI and big data analytics submissions.
For more such updates and perspectives around Digital Innovation, IoT, Data Infrastructure, AI & Cybsercurity, go to AI-Techpark.com.
