PhD Position Real-time Image Corrections for Live-television
If you like sporting events & imaging physics this might be your PhD project.You will develop methods to automatically combine live-streams from many cameras to give TV-viewers a stadium experience.
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 38 - 38 uur
- € 2395 - € 3061 per maand
This PhD project is part of a larger national program “Synoptics” with several high-tech imaging industrial partners and universities involved. In this particular project Grass Valley from Breda is the industrial partner. Grass Valley produces equipment for media and entertainment industry in particular for live-television. The branch in Breda has a particular interest and history in developing cameras for live-stream television.
The researcher will work largely at the TU Delft under the guidance of the university supervisor, but also in close collaboration with the company in Breda. The researcher will study and develop methods how to automatically combine the live-streams from many cameras for e.g. sport events. In particular for motor sport or football many cameras are used to capture the action from all angles and sides in real time. For example during a Champions league match 14-30 cameras are positioned around a football field and more than 200 people are involved in the technique to broadcasting at the station. The television viewer at home wants to have the same viewing experience has she or he would be in the stadium. The colours from all cameras must be experienced the same independent of changing shading due to clouds or sun movement and camera hardware etc. Currently this tasks is performed by manual “shaders” who control via a large board all settings either in a remote studio or an outside broadcast van. Automation of this complex task can be approached from two directions, either by modelling the signal chain and camera hardware models or by machine learning, that is learning the correct actions from examples of the manual shaders in a network.
Research in the department of Imaging Physics is aimed at developing novel instrumentation and methodology in imaging science and sensing technology. Our research products extend existing boundaries in terms of spatial resolution, temporal resolution and information/data throughput. We are pioneers in developing advanced concepts of computational imaging, a marriage between cleverly designed imaging systems and sophisticated post-processing. In everything we do, there is a core of cutting edge physics and engineering of high-tech instruments, of the use of the most advanced computing techniques, and of a very close link to real-life applications. Our work has clear societal impact in the areas of life sciences, healthcare, and industry.
You will work under the guidance of Bernd Rieger at TU Delft at the Department of Imaging Physics. His research interests focuses on the field of Computational Microscopy and Computational Imaging at large. That is combining imaging physics and image processing to reveal information in images that otherwise would be undetectable.
You must hold a MSc. degree in Electrical Engineering or Applied Physics and must have a strong background in numerical simulations and multi-parameter estimation problems. Strong programming skills are expected. Experience with machine learning (deep learning) and image processing is beneficial but not required.
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
For information about this vacancy, you can contact Prof. dr. Bernd Rieger, email: email@example.com, tel: +31 15 278 8574.