V-Nova Adds Machine Learning To Encoder

Compression specialist V-Nova has added Machine Learning capabilities to its PERSEUS Pro codec. This has been implemented into V-Nova’s P.Link encoder/decoder hardware.

The demand for higher definition video, delivered over existing network infrastructure, is placing more strain on operators and their network providers, who desperately need efficient codecs to avoid costly upgrades to their connections, according to Guido Meardi, CEO and co-founder at V-Nova.

“P.Link and the PERSEUS Pro codec that powers it had already revolutionized the contribution space by enabling studio-quality, intra-only HD and UHD at vastly lower bitrates than existing solutions. With our machine-learning advances, we’re now able to deliver visually lossless UHD at just 140Mbps, which is comparable with what many operators are currently using to deliver HD [DPP recommendations on JPEG-2000 delivery for HD].”

PERSEUS Pro is claimed to have huge efficiency gains over J2K and MPEG4 solutions. By incorporating Machine Learning and more specifically, Convolutional Neural Networks the codec “has been trained to identify common video features such as edges and curves. By identifying those features across the various layers, the amount of residual data required for reconstruction is reduced and allows PERSEUS Pro to deliver a truly accurate picture, even at lower bitrates.”

You might also like...

Computer Security: Part 5 - Dual Bus Architecture

In the UK we have Oxford v Cambridge. In the USA it’s Princeton v Harvard. The only difference is that one is a boat race and the other is computer architecture race.

Is Remote Operation Underrated?

A recent Lawo remote activities case study notes, “It should be obvious by now that remote operation has been seriously underrated. For some, it allows to save substantial amounts of money, while others will appreciate the time gained from not…

Computer Security: Part 4 - Making Hardware Secure

The history of computing has been dominated by the von Neumann computer architecture, also known as the Princeton architecture, after the university of that name, in which one common memory stores the operating system, user programs and variables the programs…

Transitioning to Broadcast IP Infrastructures; Part 3 - Delivering Operational Reliability

Our first Essential Insights is a set of three video episodes in which we discuss transitioning to IP with industry experts. We explore the fundamental challenges during the planning stage. The decisions that need to be made, and the long-term…

Latency Remains Thorn In Side Of Live Sports Remote Production

After years of trial and error designed to reduce operating cost and (more recently) keep crews safely distanced, remote production has found its niche in live production and will remain the de facto method for producing events over a distributed…