About the project
How can underwater sound and shore-based vision work together to monitor vessels more effectively? This PhD explores machine learning and multimodal fusion to improve vessel detection, characterisation and tracking in rivers and coastal waters, and to enhance acoustic monitoring using knowledge gained from vision when cameras can no longer observe.
Cameras provide information about vessel positions, sizes, types, numbers, speeds and directions of travel. Underwater sound provides complementary evidence beyond camera coverage and when visual observations are unreliable. How can these modalities improve maritime monitoring together, and how can visual knowledge strengthen acoustic monitoring?
You will develop machine learning and sensor fusion methods combining hydrophone arrays, shore-based cameras and, where available, Automatic Identification System (AIS) data. The research will investigate when multimodal sensing outperforms individual modalities, how knowledge and prior information gained from multimodal observations can enhance acoustic-only monitoring, and how uncertainty associated with each modality can inform vessel localisation and tracking.
Potential approaches include cross-modal representation learning, knowledge transfer between modalities, uncertainty-aware fusion, and probabilistic tracking informed by vessel characteristics and motion. Particular attention will be given to associating acoustic and visual observations and maintaining robust monitoring as sensing conditions and sensor availability change.
Initial studies will focus on rivers and constrained coastal navigation routes, using known sensor locations and waterway geometry to support acoustic localisation. Multimodal, vision-only and acoustic-only approaches will be evaluated for vessel detection, characterisation and tracking, testing robustness to degraded sensing and missing modalities, and generalisation to previously unseen vessels.
You will build on an existing field dataset, with hydrophone arrays, cameras and the University of Southampton’s Iridis high-performance computing facilities available. Further field measurements can extend the dataset. The supervisory team brings complementary expertise in underwater acoustics, signal processing and maritime engineering, supporting research with applications in waterway management and future autonomous vessel operations.
The School of Engineering is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
