- Balfour Beatty, High Speed 2 (HS2) Ltd.
Applications are invited for a prestigious, fully-funded PhD scholarship focusing on developing next-generation computer vision algorithms for the automatic generation of digital twins for complex construction sites to improve operational safety and overall site performance. The PhD student will use state-of-the-art computer vision and trajectory analysis algorithms to automatically analyse the interactions between workers and equipment on construction sites with complex and dynamic layouts. The algorithms and models to be developed will incorporate aspects of behavioural modelling to recognise intent and classify complex multi-agent interactions. This work will help identify hazardous construction site configurations and problematic operating regimes and will be used to inform layout modifications that ultimately improve safety performance.
The PhD student will be based in the Centre for Transport Studies in the Department of Civil and Environmental Engineering (Skempton Building, South Kensington Campus), working closely with researchers in the Department of Electrical & Electronic Engineering and industrial collaborators.
Recent advances in computer vision algorithms, alongside trajectory analysis models stemming from autonomous vehicle R&D efforts, have the potential to revolutionise safety modelling across a broad range of transport-related disciplines. One such application opportunity can be found in the analysis of industrial environments that host complex interactions between workers and equipment. Construction sites, in particular, are particularly challenging, given the largely unstructured and variable nature of activities, evolving layouts, and varying weather and lighting conditions.
The project will be carried out in close collaboration with key stakeholders from the construction industry. Given the large quantities of data involved, a key priority of this study would be to develop novel algorithms that are computationally efficient and capable of processing inputs from a variety of monitoring angles. Trajectory analysis and behavioural modelling algorithms will be applied in the resulting digital-twin representations to assess safety performance levels and make recommendations for their improvement.
Academic requirements and experience:
- A First Class Degree (or international equivalent) in an Engineering subject.
- A Masters level degree qualification.
- Experience with scientific programming languages and frameworks (such as Python, Matlab, C++) and relevant toolkits (ideal expertise includes: PuLP, NumPy, OpenCV).
- Strong interest in transportation, computer vision and machine learning.
- Excellent English communication skills.
How to apply:
Applicants wishing to be considered for this opportunity should send the following application documents to Dr Panagiotis Angeloudis ([Email Address Removed]):
- Current CV including details of their academic record and, if possible, class ranking
- Covering letter explaining their motivation, suitability, skills and experiences (1-page maximum)
- Contact details of two academic referees
Applications will be regularly reviewed until the position is filled. Please contact Dr Panagiotis Angeloudis for further particulars, informal discussions, and information about the project.
Administrative questions should be emailed to [Email Address Removed]