The HELP Video! research project will enable multimedia development companies to stay in control of their video processing and- intellectual property (IP) roadmap, boosting their competitiveness. It allows industrial partners to gain expertise in creating and optimizing video processing algorithms, and in tailoring them to address specific and diverse application needs. The project also introduces a novel design methodology for implementing video processing algorithms on heterogeneous embedded platforms, with portability and scalability as design goals.
Leaping hurdles means gaining control over IP development
Developing state-of-the-art video processing algorithms doesn’t come cheap or easy. Many multimedia companies outsource this activity or license third party IP. As a result, they lose some control over their product development. The endless proliferation of new video standards and hardware platforms makes it even more challenging to keep up. This is where HELP Video! steps in.
Pushing the limits of embedded video processing
The HELP Video! project consortium will push the limits of embedded video processing. It is structured around three key elements:
- Heterogeneous embedded platforms (hardware/software);
- Embedded low-latency video processing and its algorithmic aspects;
- Future-proof design methodology for portable and scalable IP.
The consortium consists of key industry players eSaturnus, Televic Conference and Easics, and leading university research groups imec - Data Science Lab and UGent - HES group.
Addressing cross-domain challenges
HELP Video! addresses important challenges that affect several video processing applications, including:
- the challenges caused by the combination of low-latency and low power consumption, such as in medical clinics like eSaturnus’ SMART hospital rooms and in Televic’s video conferencing codec;
- the lack of a “one-fits-all” solution that covers the entire range of performance points (ex. from TV-quality all the way up to 8K at 60 frames per second);
- the fact that both hardware platforms and video processing algorithms and standards evolve continuously and rapidly.
- The multi-disciplinary HELP Video! project consortium will overcome these challenges by combining a profound understanding of video processing algorithms with a matching design methodology.
Three concrete goals, two real-life industry applications
The three HELP Video! goals are:
- to devise and implement demanding video processing algorithms optimized for feature extraction;
- to devise and implement low-latency video processing algorithms that enhance quality of experience (QoE) in the case of unreliable network connections;
- to develop a design methodology that helps scaling video processing applications towards multiple performance points (e.g., video bandwidth and algorithm parameters such as accuracy or size of a search space), with minimal development effort.
"The HELP Video! project seeks to help multimedia industry partners master cutting-edge video processing algorithms. In addition, it will enable them to implement such algorithms using a novel design methodology that works smoothly with a multitude of embedded platforms and focuses on portability and scalability."
Hardware Platforms for Embedded, Efficient, Low-Latency and Portable Video Processing
HELP Video! is an imec.icon research project funded by imec and Agentschap Innoveren & Ondernemen.
It started on 01.10.2016 and is set to run until 30.09.2018.
- Televic Conference
- imec - IDLab - UGent
- UGent - Hardware and Embedded Systems
- Project Lead: Thomas Koninckx
- Research Lead: Filip Louagie
- Program Manager: Dirk Hamelinck