Media Excel’s AI-empowered DIVA reduces 20% bandwidth usage
Media Excel, a provider of live video encoding and transcoding solutions, will showcase its new artificial intelligence (AI)-based Dynamic Intelligent Video Adaptive (DIVA) encoding technology at IBC2024.
DIVA encoding’s innovative approach maximises efficiency by performing real-time analysis of incoming video streams, dynamically adjusting encoding settings, and optimising codec performance. This technology achieves visual video quality while delivering a 20% or better reduction in bandwidth usage for streamed HEVC-encoded video content, said Media Excel.
Narayanan Rajan, CEO of Media Excel, added, “Our approach to leveraging AI through cutting-edge deep learning models is very pragmatic. We aim to deliver the best video visual quality while significantly reducing the cost of streaming video at scale.
“This becomes even more critical as more content owners are streaming directly to consumers, and cloud egress and content delivery network (CDN) distribution costs are starting to dominate total cost of ownership (TCO).”
The solution ensures more efficient bandwidth usage, enabling significantly reduced bandwidth consumption for both constant and variable bitrate delivery without impacting the end-experience for the viewer.
DIVA encoding will be released for general availability on Media Excel’s Hero platform later this year. It can be enabled via on-premise Media Excel Hero appliances, or in containerised Hero instances in public clouds. DIVA encoding enabled Hero systems ensure ease of implementation by integrating within existing infrastructures, simply replacing encoders or transcoders. This allows media service providers to enhance their video encoding capabilities without extensive overhauls.
“Our new technology extends the lifespan of current service chains and postpones the need to transition to new codecs. This makes it a highly cost-effective solution for service providers and content owners,” said Narayanan.To find out more, visit the Media Excel team at booth 1.F51 during IBC2024, which is taking place at the Amsterdam RAI Convention Centre from September 13-16.
