About the Project
We are seeking a motivated person interested in a self-funded doctoral study PhD degree. With the training provided, the PhD will research, implement solutions, and produce research papers in the exciting areas of computer vision with deep learning and multiple drones. He/she has access £124,000 worth of equipment to carry out these goals. Extra support will be provided by the supervisor and other PhDs in the team.
Taking advantages of the recent advancements in deep learning and drone systems, new applications and breakthroughs in computer vision have become possible. Areas such as surveillance, recognition, crowd analysis and 3D reconstruction, have shown significant improvements in recent years. In this project, the PhD will research on state-of-the-art deep learning algorithms. With multiple video input simultaneously, vision-based methods are to be developed to understand and analyse the content. We are interested in all sort of computer vision problems, and are particularly interested in utilizing the multi-drones systems to analyze the flow of people/vehicle movement, as well as to reconstruct the 3D shape of the people from multiple 2D view input.
The PhD will be supervised by Dr. Hubert Shum (http://info.hubertshum.com), who is the Director of Research and Innovation in the Department. He organized international conferences such as BMVC and ACM SIGGRAPH MIG, and is an Associate Editor of CGF and a Guest Editor of IJCV.
The job is based in the Department of Computer and Information Sciences, located in a new £7m purposefully designed building. It is placed by the Times Higher Education World Ranking 2019 in the top 250-300 for computer science, and is one of the largest computer science departments in the UK.
This project is supervised by Dr. Hubert Shum.
Eligibility and How to Apply:
Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
• Desirable: experience in one or more modern programming languages.
• Desirable: experience in one or more of the following areas: computer vision/graphics, deep learning, drone/robotic controls.
For further details of how to apply, entry requirements and the application form, see
https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/
Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. SF19/EE/CIS/SHUM) will not be considered.
Start Date: 1 March 2020 or 1 October 2020
Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community. The University holds an Athena SWAN Bronze award in recognition of our commitment to improving employment practices for the advancement of gender equality and is a member of the Euraxess network, which delivers information and support to professional researchers.
References
• He Wang, Edmond S. L. Ho, Hubert P. H. Shum and Zhanxing Zhu, "Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling," IEEE Transactions on Visualization and Computer Graphics, IEEE, 2019.
• Lining Zhang, Hubert P. H. Shum, Li Liu, Guodong Guo and Ling Shao, "Multiview Discriminative Marginal Metric Learning for Makeup Face Verification," Neurocomputing, vol. 333, pp. 339-350, Elsevier, 2019.
• Dimitrios Sakkos, Edmond S. L. Ho and Hubert P. H. Shum, "Illumination-aware Multi-task GANs for Foreground Segmentation," IEEE Access, vol. 7, no. 1, pp. 10976-10986, IEEE, 2019.
• Yijun Shen, Joseph Henry, He Wang, Edmond S. L. Ho, Taku Komura and Hubert P. H. Shum, "Data-Driven Crowd Motion Control with Multi-touch Gestures," Computer Graphics Forum, vol. 37, no. 6, pp. 382-394, John Wiley and Sons Ltd., 2018.
• Lining Zhang, Hubert P. H. Shum and Ling Shao, "Manifold Regularized Experimental Design for Active Learning," IEEE Transactions on Image Processing, vol. 26, no. 2, pp. 969-981, IEEE, Feb 2017.