To be considered for the project, candidates must:
- Hold, or be about to gain, a 1st class UK BEng Honours degree or MSc with Distinction, in a relevant engineering, physics or data science related subject
- Have understanding and technical knowledge of artificial intelligence, machine learning and engineering data methods
- Possess Programming skills: Python, Matlab, R, C++
- Have a strong mathematical background
- Be highly motivated, independent and results-orientated, with excellent team-working skills
- Be a UK or eligible EU national and adhere to Research Council (RCUK) eligibility criteria
Expertise in experimental research in signal analysis would also be preferable.
Eligibility for RCUK studentships
- Research Council (RC) fees and stipend can only be awarded to UK and EU students and not to EEA or International students.
- EU students are only eligible for RC stipend if they have been resident in the UK for 3 years, including for study purposes, immediately prior to starting their PhD.
- If an EU student cannot fulfil this condition then they are eligible for a fees only studentship.
- International students cannot be funded from RC funds unless they are ‘settled’ in the UK. ‘Settled’ means being ordinarily resident in the UK without any immigration restrictions on the length of stay in the UK. To be ‘settled’ a student must either have the Right to Abode or Indefinite leave to remain in the UK or have the right of permanent residence in the UK under EC law. If the student’s passport describes them as a British citizen they have the Right of Abode.
- Students with full Refugee status are eligible for fees and stipend.
Oil & Gas operators are required to carry out inspections of their subsea pipelines and platforms for insurance and legal purposes. This is carried out on an annual or bi-annual basis to check the integrity of the asset, to ensure there are no leaks or damage through corrosion, the impact from e.g. fishing nets or from natural causes. Whilst, there have been many advances in technology, Inspection, Maintenance and Repair (IMR) still requires significant human intervention. A Data Coordinator provides an ongoing commentary on the video feed that is received from the ROV. This role is typically delivered by the contractors, leading to high costs and inconsistent quality. The video and commentary are then Quality Checked (QC), usually once the survey is completed, creating a bottleneck in reporting.
The aim of the project is to perform edge processing and automate the video annotation using deep convolutional neural networks to permit fast and automatic annotation of subsea survey video frames. This reduces the need for human intervention, increases consistency and accuracy. Further, it permits real-time transmission of relevant video and sensor data segments from the ship-to-shore for immediate QC. Both of these aspects will increase survey speed and reduce the cost to the O&G inspection industry.
This PhD programme will be structured around three topics:
- Neural networks are revolutionising image analysis. From facial recognition software to dense image captioning and fuel leaps in the ability to process and analyse video data. Leveraging the latest in deep neural networks and video processing will permit to automatically generate annotations of inspection repair maintenance survey videos. The developed video analytics framework will automatically annotate all events of interest. Particularly challenging are infrequent events with faint features or with high variation in appearance due to lack of representative training data. Generative and self-learning approaches will be studied to mitigate the lack of data and fine tune the trade-off between false negatives and positives (i.e. sensitivity)
- Remote Operating Vehicles (ROVs) are equipped with multiple sensors such as multi-beam, side-scan, magnetometers, positioning, photogrammetry, laser, etc. These additional sensing modalities will be utilised to mitigate classification annotation uncertainty by combining data sources.
- Development of context aware compression techniques will offer the potential to significantly reduce the communication bandwidth requirements and enable transmission of survey data to shore in real-time. This project task will investigate the communications management framework for data transmission.
The PhD will commence on 1st october 2018.
Funding is provided for full tuition fees (UK / EU applicants only), along with a generous stipend and support with travel costs for meetings, conference attendance and publications.
The primary supervisor will be Dr Christos Tachtatzis, Lecturer in Centre for Intelligent Dynamic Communications within the Institute for Sensors, Signals and Communications (ISSC) in the Department of Electronic & Electrical Engineering. Dr Tachtatzis’ research interests include edge data analytics and computer vision.
The secondary supervisor will be Professor Craig Michie, Head of the Centre for Intelligent Dynamic Communications within ISSC. Professor Michie’s research expertise is in data analytics and communication systems.
How to apply
Candidates interested in applying should first email Dr Christos Tachtatzis or tel: +44 (0)141 548 2625 for an informal discussion. Thereafter, they should submit their CV, academic transcript, and a covering letter outlining their suitability for the position.
Following review of the application submissions, selected candidates will be invited for interview.
Application submission deadline is 30 April 2018.
The PhD project will start on 1 October 2018.