The demand for video processing is rapidly increasing, driven by greater numbers of sensors with greater resolution, new types of sensors, new collection methods and an ever wider range of applications. For example, video surveillance, vehicle automation or wildlife monitoring, with data gathered in visual/infra-red spectra or SONAR, from multiple sensors being fixed or vehicle/drone-mounted.
This project will focus on a specific application – object (animal) extraction and classification from extremely high-resolution aerial video from moving platforms. Issues of data size, dynamic backgrounds, rapid platform and target movement and classification errors will all need to be resolved and propagated into the final goal – inferring the densities of target species.
The project will require solving substantive computational bottlenecks and creative programming e.g. GPU and distributed file systems. Elements can be found in Erichson & Donovan (2016), but is only a tiny fraction of what is required.
For more information, please see the School's Postgraduate Research page, and in particular the information about Statistics PhD opportunities.
Full funding (fees, plus stipend of approx. £15,840) is available for well-qualified students; we encourage applications as soon as possible to maximize your chances of being funded. UK, EU and other overseas students are all encouraged to apply. New PhD students would typically start in September 2022, but this is flexible. More information is available School's Postgraduate Research web page -- please see the link at the bottom of the project description.
Lancaster University, Bailrigg, Lancaster, UK
October 01, 2022
Imperial College London
September 01, 2022
King’s College London
King's College Hospital, Denmark Hill, London, UK
October 01, 2022