Project code



School of Computing

Start dates

October, February and April

Application deadline

Applications accepted all year round

Applications are invited for a self-funded, 3 year full-time or 6 year part-time PhD project.

The PhD will be based in the school of computing and will be supervised by Dr Gelayol Golcarenarenji, Dr Rahim Taheri and Dr Alex Gegov.

The work on this project could involve:

  • Design and prototype an AI-based fast vision-based pipeline for the effective detection of objects (e.g., human) in UAV imagery in real time based on Transformer-based CNN methods to increase accuracy. 
  • Use NAS and Hardware Neural Architecture Search (HW-NAS) methods to further increase the performance in terms of accuracy and latency.
  • Develop the proposed algorithm on low-powered computers (e.g., Jetson Xavier) on the edge to increase data security and privacy.


Unmanned Aerial Vehicles (UAVs) are promising technologies within a myriad of application scenarios. However, adverse conditions, such as varying altitude, small objects, changing illumination and moving platform, impose challenges for high-performance. Small object detection is still one of the most unresolved and challenging detection problems due to the extraction of feature information of small objects being difficult with only a few pixels. It is very hard for standard detectors to distinguish small objects from generic clutters in the background. These challenges have a detrimental influence on the accuracy and performance and should be taken into consideration in UAV applications.  It is of high importance for the developed object detectors to be highly accurate and efficient when it comes to surveillance and security systems. To improve the accuracy of these, extensive research for improved performance has been performed on a wide range of hyper-parameters, such as network structures, weight initialization, activation functions, operators, loss functions. However, it needs technical expertise and understanding and a significant amount of engineering time. 

The NAS method is an intelligent algorithm to automatically search for an efficient neural architecture to save the researcher’s manual effort and computation time.

Hence, the aim of this project is to design and develop a novel real-time portable cost-effective machine-learning-based small object detection system on UAV-based images with high-accuracy using NAS and HW-NAS methods to consider hardware constraints suitable for surveillance and security systems.


Visit the research subject area page for fees and funding information for this project.

Funding availability: Self-funded PhD students only. 

PhD full-time and part-time courses are eligible for the UK Government Doctoral Loan (conditions apply).

Bench fees

Some PhD projects may include additional fees – known as bench fees – for equipment and other consumables, and these will be added to your standard tuition fee. Speak to the supervisory team during your interview about any additional fees you may have to pay. Please note, bench fees are not eligible for discounts and are non-refundable.

Entry requirements

The entry requirements for a PhD or MPhil include an upper second class honours degree or equivalent in a relevant subject or a master's degree in an appropriate subject. Exceptionally, equivalent professional experience and/or qualifications will be considered. All applicants are subject to interview.

If English is not your first language, you'll need English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

If you don't meet the English language requirements yet, you can achieve the level you need by successfully completing a pre-sessional English programme before you start your course.


You should have computer programming knowledge using R or Python.


How to apply

We’d encourage you to contact Dr Gelayol Golcarenarenji ( to discuss your interest before you apply, quoting the project code.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV.  Our ‘How to Apply’ page offers further guidance on the PhD application process. 

When applying please quote project code: COMP6341025