About the Project
Project Description: There is a hunger for new, more immersive video content from consumers, producers and network operators. Efforts in this area have focused on extending the video parameter space with greater dynamic range, increased spatial and temporal resolutions, wider colour gamut, enhanced interactivity through 360 degree content, larger displays and, of course, the full stimulation of peripheral vision through head-mounted displays that provide a greater sense of immersion for many users. There is however, a very limited understanding of the interactions between the dimensions in this extended parameter space and their relationship to content statistics, visual engagement and delivery methods. The way we represent these immersive video formats is thus key in ensuring that content is delivered at an appropriate quality, which retains the intended immersive properties of the format, while retaining compatibility with the bandwidth and variable nature of the transmission channel. Major research innovations are needed to solve this problem.
The research challenges to be addressed are based on the hypothesis that, by exploiting AI methods to capture the perceptual properties of the Human Visual System, and its content-dependent performance, we can obtain step changes in visual engagement while also managing bit rate. Deep learning methods have made significant advances in recent years and are now able to analyse and classify visual scenes with a performance approaching that of a human. Our objectives are therefore: i) to understand the perceptual relationships between video parameters and content type; and ii) to develop new visual content representations that adapt to content statistics and their immersive requirements. Solutions to will develop new machine (deep) learning methods to classify scene content, optimized using perceptual loss functions, and relate this to the extended video parameter space.
The person: We are seeking a person with an interest in video processing and scene understanding, exploiting an understanding of perceptual processes. The person would ideally have an undergraduate or Master’s degree in a relevant discipline such as Computer Science, or Electronic Engineering, or could be from other numerate disciplines of from psychology with a strong mathematical background. Due to the interdisciplinary nature of this work, applicants with different scientific backgrounds will also be considered.
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.