PhD Studentship: Advancing Automation in Aerial Imaging for Marine Litter Detection (CASE project with Cefas) University of East Anglia in United Kingdom

[Fully-funded studentship covering fees, maintenance stipend (£20,780 p.a. for 2025/26), and research training and support grant (RTSG). International applicants may have the difference between 'home' and 'international' fees waived, but relocation and visa costs are not covered.] This PhD studentship at the University of East Anglia, in partnership with Cefas, focuses on advancing automation in aerial imaging for marine litter detection. Marine litter poses a significant threat to ocean health and livelihoods, necessitating scalable, automated methods for data collection and analysis. Cefas has developed a visible light deep learning algorithm and amassed a large training dataset covering 89 litter categories. However, to improve the accuracy of material type identification, the project will incorporate multispectral imagery and develop a new laboratory for characterising multispectral reflectance of materials. The successful candidate will use the existing visible light database and collect new multispectral data with the enhanced lab setup, aiming to train robust deep learning algorithms. These algorithms must be resilient to real-world illumination changes and adaptable to future imaging devices with unknown spectral sensitivities. The research will involve developing a multispectral imaging dataset of marine litter materials, designing and evaluating deep learning models for classification, implementing device-independent representations, and applying domain adaptation and transfer learning techniques to generalise models across different devices. The student will be based in the Colour & Imaging Lab at the School of Computing Sciences, benefiting from expertise in imaging solutions and opportunities to collaborate with scientists and engineers at Cefas. Training will include imaging principles, lab measurement, computer vision, ArcGIS, fieldwork, and UAV flying. Applicants should have a UK equivalent Bachelors (Honours) 2:1 in Computer Science, Physics, Maths, or a related numerate discipline, with experience or interest in environmental monitoring, AI, computer vision, or multispectral imaging. English language proficiency (IELTS 6.5 overall, 6 in each category) is required. The studentship is fully funded for eligible UK and international candidates, covering fees, a maintenance stipend (£20,780 p.a. for 2025/26), and a research training and support grant. International students may have the fee difference waived, but relocation and visa costs are not covered. The position is full-time, starting 1 October 2026, with an application deadline of 7 January 2025.