Funding

Self-funded

Project code

CMP10011025

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.

The work on this project will:

  • Design and prototype a computer-vision based solution for the effective prediction of human trajectory in UAV imagery in real time with high accuracy.
  • Develop the proposed algorithm on low-powered computers (e.g., Jetson Xavier) on the edge to increase data security and privacy.

Predicting human motion trajectory in a complex urban environment has myriad of applications specially in intelligent transportation, autonomous driving, smart cities, Surveillance systems among others. For instance, potential collisions can be avoided by predicting the behavior of the person in advance to save lives.  In addition, large crowds can be controlled and monitored for suspicious behaviors. However, randomness and complexity of human motion, the internal and external stimuli, mental and social factors make this task very challenging. 

Unmanned Aerial Vehicles (UAVs) are promising technologies within a myriad of application scenarios such as search and rescue and surveillance. However, adverse conditions, such as varying altitude, small objects, changing illumination and moving platform, impose challenges for high-performance. 

Recurrent Neural Networks (RNNs) — such as Gated Recurrent Units (GRUs), Long-Short Term Memory (LSTM), Convolutional LSTMs (ConvLSTMs) or combination, (GANs) and Variational Autoencoders (VAEs) are promising approaches in this field. However, there are shortcomings when it comes to accuracy.

Hence, the aim of this project is to design and develop a novel real-time portable cost-effective computer-vision-based human motion prediction on UAV-based images with high-accuracy suitable for intelligent transportation systems, surveillance among others.

 

 

Fees and funding

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 (UK and EU students only).

 

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

You'll need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a master’s degree in computer science or a related area. In exceptional cases, we may consider equivalent professional experience and/or Qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

You should have computer programming knowledge using Python, Pytorch or Tensorflow.

 

 

How to apply

We’d encourage you to contact Dr Gelayol Golcarenarenji (gelayol.golcarenarenji@port.ac.uk) 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: CMP10011025