Scalable Stream Coding for Adaptive Foveation Enhanced Percept Multimedia Information Communication for Interactive Medical Applications

摘要

Project Perceptmedia is one of the few projects within the Active Network Initiative (ANI) to conduct a top down investigation into active networking from the point of view of realistically complex high performance applications. The project developed a suit of futuristic active applications based on the core idea of media transcoding. It then closely examined the issues if such complex active services were to run from network embedded router centric computing platforms contemplated in ANI. The demonstrated systems include interactive perceptual transcoding where real-time eye-tracker data fuses with a passing stream, the active subnet diffusion coding-- where multiple active nodes dynamically and adaptively aggregate to tackle intense tasks, and the active video content filtering and analysis. The research produced several novel algorithmic contributions to the field including the first algorithms for active computing mapping, jitter and delay reduction in active computing, and an IPV6 based novel mechanism for fast traffic interception. The project produced proof of concept implementations for almost all of these ideas.