Advancing Automation in Aerial Imaging for Marine Litter Detection, CASE project with Cefas

Advancing Automation in Aerial Imaging for Marine Litter Detection, CASE project with Cefas

Project Description

Supervisors

Professor Michal Mackiewicz, School of Computing Sciences, University of East Anglia

Professor Graham Finlayson, School of Computing Sciences, University of East Anglia

Dr Julie Bremner, Cefas and Hon. Senior Lecturer at University of East Anglia

Mr Peter Kohler, Centre for Environment, Fisheries and Aquaculture Science (Cefas)

 

Scientific Background

Marine litter is a key threat to the oceans’ health and the livelihoods. Hence, new scalable automated methods to collect and analyse data are needed to enhance our understanding of sources, pathways and impact of litter. Cefas is developing a visible light (VL) deep learning (DL) algorithm and collected a large 89 litter category training dataset. However, there is a recognition of the need of multispectral imagery to enhance the accuracy of the algorithms being developed when discerning material type. Consequently, Cefas is developing a new lab to assist in characterisation of multispectral reflectance of materials.

 

Research Methodology

The student will utilise the existing VL database of key materials, but importantly will also collect multispectral data with the enhanced lab setup with an aim to train the DL algorithms. Importantly, the algorithms developed must be robust to changing real-world illumination and utilised long-term, likely with imaging devices not existing during the development. This will require an approach that considers the physics of the multispectral image formation including the three key variables: sensor spectral sensitivities, varying daylight illumination spectrum and wide range of relevant material reflectance spectra.

 

Objectives

Develop a multispectral imaging dataset of marine litter materials by extending the existing VL dataset.

Design and evaluate DL models capable of classifying marine litter types using multispectral data, with a focus on achieving robustness to varying spectral channel configurations and illumination conditions.

Implement and validate device-independent representations. Investigate and apply domain adaptation and transfer learning techniques to develop models that generalize across different imaging devices, including future sensors with unknown spectral sensitivities.

 

Training

The student will be based at the Colour & Imaging Lab at the School of Computing Sciences which has expertise in the design and evaluation of imaging solutions and will have an opportunity to work with scientists and engineers at Cefas. They will undertake training specific to this project including imaging principles, lab measurement, computer vision and ArcGIS, potential fieldwork and UAV flying training.

 

Person Specification

Experience and/or enthusiastic interest in one or more of the following areas: environmental monitoring, AI, computer vision or multispectral imaging.

Acceptable first degree subjects: BA in Computer Science/Physics/Maths or other numerate discipline.

Project code: MACKIEWICZ_UEA_ARIES26_CASE

All ARIES CASE studentships include a three to 18-month placement with the non-academic CASE partner during their period of study. The placement offers experience designed to enhance professional development.

References

  • Rangel-Buitrago, N., Williams, A. T., Neal, W. J., Gracia C, A., & Micallef, A. (2022). Litter in coastal and marine environments. Marine Pollution Bulletin, 177(February). doi: 10.1016/j.marpolbul.2022.113546
  • Yang, Z., Yu, X., Dedman, S., Rosso, M., Zhu, J., Yang, J., Xia, Y., Tian, Y., Zhang, G., & Wang, J. (2022). UAV remote sensing applications in marine monitoring: Knowledge visualization and review. Science of the Total Environme
  • B. Hobley, M. Mackiewicz, J. Bremner, T. Dolphin and R. Arosio, "Crowdsourcing Experiment and Fully Convolutional Neural Networks for Coastal Remote Sensing of Seagrass and Macroalgae," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 8734-8746, 2023, doi: 10.1109/JSTARS.2023.3312820
  • Hobley, B.; Arosio, R.; French, G.; Bremner, J.; Dolphin, T.; Mackiewicz, M. Semi-Supervised Segmentation for Coastal Monitoring Seagrass Using RPA Imagery. Remote Sens. 2021, 13, 1741. doi: 10.3390/rs13091741
  • Garaba, S. P., & Dierssen, H. M. (2018). An airborne remote sensing case study of synthetic hydrocarbon detection using short wave infrared absorption features identified from marine-harvested macro- and microplastics. Remote Sensing of Environment, 205(April 2017), 224–235. doi:10.1016/j.rse.2017.11.023

Key Information

  • This studentship has been shortlisted for funding under the UKRI NERC DLA funding scheme and will commence on 1 October 2026. The closing date for applications is 23:59 on 7 January 2026.
  • Successful candidates who meet UKRI’s eligibility criteria will be awarded a fully-funded studentship, which covers fees, maintenance stipend (£20,780 p.a. for 2025/26) and a research training and support grant (RTSG). A limited number of studentships are available for international applicants, with the difference between 'home' and 'international' fees being waived by the registering university. Please note, however, that ARIES funding does not cover additional costs associated with relocation to, and living in, the UK, such as visa costs or the health surcharge.
  • ARIES postgraduate researchers (PGRs) benefit from bespoke training and ARIES provides £2,500 to every student for access to external training, travel and conferences, on top of all Research Costs associated with the project. Excellent applicants from quantitative disciplines with limited experience in environmental sciences may be considered for an additional 3-month stipend to take advanced-level courses. Excellent applicants from quantitative disciplines with limited experience in environmental sciences may be considered for an additional 3-month stipend to take advanced-level courses.
  • ARIES is committed to equality, diversity, widening participation and inclusion in all areas of its operation. We encourage enquiries and applications from all sections of the community regardless of gender, ethnicity, disability, age, sexual orientation and transgender status. Academic qualifications are considered alongside non-academic experience, and our recruitment process considers potential with the same weighting as past experience.
  • All ARIES studentships may be undertaken on a part-time or full-time basis. International applicants should check whether there are any conditions of visa or immigration permission that preclude part-time study. All advertised project proposals have been developed with consideration of a safe, inclusive and appropriate research and fieldwork environment with respect to protected characteristics. If you have any concerns, please contact us.
  • For further information, please contact the supervisor. To apply for this Studentship, follow the instructions at the bottom of the page or click the 'apply now' link.
  • ARIES is required by our funders to collect Equality and Diversity Information from all of our applicants. The information you provide will be used solely for monitoring and statistical purposes; it will remain confidential and will be stored on the UEA SharePoint server. Data will not be shared with those involved in making decisions on the award of Studentships and will have no influence on the success of your application. It will only be shared outside of this group in an anonymised and aggregated form. You will be asked to complete the form by the University to which you apply.
  • ARIES studentships are subject to UKRI terms and conditions. Postgraduate Researchers are expected to live within reasonable distance of their host organisation for the duration of their studentship. Please see https://www.ukri.org/publications/terms-and-conditions-for-training-funding/ for more information.

Apply Now

Apply now via the  University of East Anglia Application Portal