Customers will be able to use these capabilities on Xilinx devices, including the integrated Zynq UltraScale+ MPSoC platform for AI edge processing. The combination of real-time audio and video processing, AV connectivity interfaces, codecs, IP networking, CPU, and GPU into an adaptable and scalable single-chip solution is intended to provide users with significant space, power, and cost savings.
“Machine learning is a rapidly developing technology that is stimulating new usage models in Pro AV and broadcast,” said Ramesh Iyer, director of Pro AV & Broadcast at Xilinx. “Adding ML into Xilinx’s adaptable platforms provides a highly integrated AV processor that delivers proven support for 8K video, AV-over-IP, and compression, and now adds advanced capabilities for monetizing analytics, improving workflow efficiency and enhancing usability. Ultimately, these integrated ML features will allow companies to increase innovation, differentiate themselves, and accelerate time-to-market.”
Pro AV market customers can apply the new ML capabilities across a number of applications and workloads, including:
Region-of-Interest Encoding – detect faces and features using ML and the Zynq UltraScale+ MPSoC integrated H.264/H.265 codec to keep video quality high in those areas and apply higher compression for backgrounds. This reduces the overall bitrate and saves significant costs in live streaming.
Intelligent Digital Signage – using ML models for gender, age and gesture detection to present targeted interactive advertising in digital signage. The result is a higher return on investment for advertisers as well as monetizable behaviour metrics.
Automated Object Tracking and Window Cropping – output multiple HD windows from a single 4K camera using ML. This is particularly useful when providing switchable content at live events and in control rooms.
Speech Recognition – automatically output text from speech, which is ideal for automating the transcription of meeting notes and language translation in conferencing and collaboration.