Partnerschaft DeepVA Hochschule RheinMain

“UPCON” — a joint research project with RheinMain University and Lynx Technik AG

Modern TVs boast stunning Ultra High Defin­ition (UHDTV) capabil­ities, but displaying scenes with high contrast and color range remains a challenge. During the conversion from standard HDTV to UHDTV, details are often lost in overly bright or dark areas.

Intro­ducing High Dynamic Range (HDR): A Brighter Future for Video

High Dynamic Range (HDR) offers a solution. HDR content delivers richer contrast, more vivid colors, and a more natural viewing experience, closer to what the human eye perceives.
SDR to HDR convertion

Bridging the Gap: Upcon­verting SDR to HDR with AI

Broad­casters face the challenge of existing library content recorded in Standard Dynamic Range (SDR). Acquiring new HDR recording equipment can be expensive, and not all cameras can capture the high contrast ranges needed for HDR. Here’s where a new research project from RheinMain University of Applied Sciences, Lynx Technik AG, and DeepVA comes in. They are devel­oping algorithms to “upconvert” (UPCON) SDR video to HDR. This technology is to be used both in real time directly during the recording of video material, and subse­quently in the form of a cloud-based, non-real time conversion. Important aspects here are scala­bility via cloud systems, the creation of an economical hardware solution for use in OB vans, and the use of AI-based image processing algorithms that are intuitively manageable and easily acces­sible for the user.

Real-time Upcon­version

Convert video directly during recording, ideal for live events.

Cloud-based

Convert existing footage stored in the cloud.

Beyond broadcast, this technology has the potential to revolu­tionize various fields. In security and surveil­lance, it can enhance image clarity for better monitoring of critical areas. For autonomous vehicles, it can improve the processing of on-board camera images, leading to more accurate virtual rearview mirrors and other driver assis­tance systems.

joint research

Collab­o­ration for Success

The RhineMain University of Applied Sciences has extra­or­dinary know-how in the field of deep learning and high-resolution television systems within the scope of the media technology course. It is respon­sible for the devel­opment of the algorithms for a modular, real-time system, capable of the execution of AI-based image processing methods.

Hochschule RheinMain

 

Lynx Technik AG is focused on the devel­opment, manufac­turing, and distri­b­ution of hardware-based special devices for profes­sional television technology. Accord­ingly, Lynx Technik AG supplies the appro­priate hardware unit to handle the complex and compu­ta­tionally intensive methods using GPU technology. The focus here is on the speed at which the data is processed in real time.

DeepVA handles the image processing without a real-time component. This takes place on a cloud platform for which the necessary AI infra­structure is already in place. The main emphasis here is on the quality of the conversion. DeepVA also supports RheinMain University with its deep learning expertise and AI knowledge.

Innovation programme

Funded by Innovation

This ambitious project is co-financed by the German Federal Ministry of Economics and Climate Protec­tion’s “Zentrales Innova­tion­spro­gramm Mittel­stand” (ZIM) initiative.

Share

Email
LinkedIn
Facebook
Twitter
Search

Table of Contents

latest AI news

Subscribe to our newsletter

Don’t worry, we reserve our newsletter for important news, so we only send a few updates once in a while. No spam!