This PhD project will advance computer vision and edge-AI for real-time, low-cost marine environmental monitoring. In collaboration with Cefas (the Centre for Environment, Fisheries, and Aquaculture Science), a global leader in marine science, the research will develop scalable embedded vision systems to enhance benthic biodiversity monitoring and detect anthropogenic debris. The core challenge lies in designing robust edge-AI sensors and algorithms capable of classifying benthic features and indicator taxa under complex underwater conditions, while reducing reliance on expensive cloud infrastructure.
The project will also explore the integration of hyperspectral imaging into biodiversity monitoring platforms. This will enable the development of algorithms for detecting taxa-specific health indicators (e.g., in seagrass species or soft corals such as Pink Sea Fan), offering more objective measures of benthic faunal health in UK waters than currently available.
Building on the Neural Network Enhanced Marine Observation system (NNEMO)—a working prototype spatial camera system for shallow waters—the project will extend its current capabilities. While NNEMO already classifies and counts indicator taxa such as sea pens, the next phase will incorporate simultaneous localisation and mapping (SLAM), hyperspectral imaging, and debris classification using in-house trained deep learning models deployed on embedded devices.
The demand for such systems arises from the high cost of vessel deployment and the time-consuming manual analysis of imagery, both of which limit data collection. Existing vision-based solutions also depend heavily on cloud infrastructure and specialist expertise. By contrast, a scalable, embedded computer vision system that analyses imagery in real time can significantly improve the efficiency and accuracy of nearshore vegetation assessment, shellfish stock monitoring, debris detection, and epibenthic biodiversity surveys.
Project Objectives:
This project is a CENTA Flagship Project.
This project is suitable for CASE funding
Each host has a slightly different application process.
Find out how to apply for this studentship.
All applications must include the CENTA application form.
Choose your application route
The PhD candidate will utilize the Depth AI Python library and SDK, alongside OpenCV and deep learning platforms such as PyTorch, in a tank-testing environment to establish stereo calibration for the NNEMO platform’s native image depth model. These calibrated spatial models will be deployed during Nephrops norvegicus and Scallop (Pecten maximus) surveys in 2026 to capture depth-enabled seabed footage. Additionally, the spatial imagery collected from these surveys, combined with data from marine protected area surveys, will support the development of models for benthic anthropogenic debris detection, scallop identification and tracking, and N. norvegicus burrow identification and network mapping.
A key objective will be to develop a pipeline for estimating organism volumes using stereo-derived image depth calculations. The models and algorithms created will then be integrated with other NNEMO platform functionalities to facilitate real-time testing.
DRs will be awarded CENTA Training Credits (CTCs) for participation in CENTA-provided and ‘free choice’ external training. One CTC can be earned per 3 hours training, and DRs must accrue 100 CTCs across the three and a half years of their PhD.
In addition to CENTA training opportunities, this PhD project will provide extensive training in artificial intelligence, computer vision, and embedded AI, with a specific focus on their application in real-time marine monitoring systems. The candidate will gain advanced skills in developing deep learning and computer vision models for underwater object detection and classification. Additionally, they will acquire expertise in robotics and embedded systems, focusing on edge computing for data collection and analysis. Through interdisciplinary collaboration with Cefas, the candidate will gain related knowledge in marine science and develop practical skills in deploying AI technologies in challenging environments such as marine applications.
Year 1: Literature Review, and Initial feasibility studies
In year 1, the student also needs to complete any required training (courses, workshops).
Year 2: Algorithms and models for scallop detection, N. norvegicus burrow identification, and benthic anthropogenic debris measurement
Year 3: Implement algorithms on an embedded AI board and conduct final experiments, result analysis, and thesis writing
Months 32-36: Write a journal paper, and finish the PhD thesis writing up.
Zhou, Y, Li, B, Wang, J, Rocco, E, Meng, Q (2022) Discovering Unknowns: Context-enhanced Anomaly Detection for Curiosity-driven Autonomous Underwater Exploration, Pattern Recognition, Vol.131, 108860. DOI: 10.1016/j.patcog.2022.108860.
H. Gary Greene, Craig J. Brown, Peter T. Harris, Kim Picard (2023) ‘Mapping anthropogenic impacts on marine benthic habits’, Continental Shelf Research, Vol 269, 105142
Shenming Qu, Can Cui, Jiale Duan, Yongyong Lu & Zilong Pang (2024), ‘Underwater small target detection under YOLOv8-LA model’, Scientific Report 14, 16108
Naseer, Atif, Enrique Nava Baro, Sultan Daud Khan, and Yolanda Vila.(2022) ‘A Novel Detection Refinement Technique for Accurate Identification of Nephrops norvegicus Burrows in Underwater Imagery’ , Sensors 22, no. 12: 4441. https://doi.org/10.3390/s22124441
Tao Song, Cong Pang , Boyang Hou, Guangxu Xu, Junyu Xue, Handan Sun and Fan Meng (2023), ‘A review of artificial intelligence in marine science’, Frontiers in Earth Science, Volume 11, https://doi.org/10.3389/feart.2023.1090185.
For further information about this project, please contact Professor Qinggang Meng ([email protected]).
To apply to this project:
Applications must be submitted by 23:59 GMT on Wednesday 7th January 2026.