SPADS CDT: Sensing, Processing, and AI for Defence and Security

Sensor Signal Processing

Sensor Signal Processing (SSP) develops Intelligence, Surveillance and Reconnaissance (ISR) concepts that can prioritize, process, and fuse large amounts of information from heterogeneous sensors on dynamic and static platforms generating data of different types and varying quality, in an efficient and timely manner.

Object tracking using neuromorphic computing and Bayesian deep learning

This project consists of developing robust neuromorphic methods for multiple object tracking

Neuromorphic computing for 3D imaging with single-photon Lidars

This project consists of developing spiking neural networks to process time-of-flight (ToF) data for 3D reconstruction from SPADS sensors.

Fusion of multiple sources of evidence using Bayesian chain event graphs

Using Bayesian graphical modelling for combining evidence to assess the likelihood of real-world events.

Advancing 3D Underwater Imaging: sensor fusion and statistical AI for enhanced robustness and interpretability

Advance 3D underwater imaging by enhancing its resilience and data resolution, thereby enabling high-level tasks such as object detection and tracking.

High-resolution Object Detection in the Sea Clutter Environments (SAAB Systems)

Complex distribution modelling of the sea clutters to improve the target detection performance in terms of ROC, TP, FP figures.

Development of spiking architectures using Bayesian deep learning

This project consists of developing robust and scalable methods to train spiking artificial neural networks

Distributed Information Fusion

This project will develop new machine learning inspired algorithms to extract, communicate and fuse information from networks of sensors, converting sensing into actionable information.

Autonomy Counter-Counter Measures (Leonardo)

Humans with experience are very able to know when something is going wrong with the system they are using and to compensate for it. In autonomous system this intuition needs to be built into the algorithmic design.

Robust non-linear state-space modeling: From filtering to deep learning approaches

The objective is to mix filtering methods with optimisation and deep learning to design advanced efficient tracking methodologies, with strong theoretical guarantees.

Model based deep learning for robust multimodal 3D imaging

The project aims to develop new computational algorithms to optimize the acquisition and processing of event data (e.g., single-photon data) and enable fast imaging in extreme environmental conditions using statistical and learning based approaches.

EPSRC and MoD CDT in Sensing, Processing, and AI for Defence and Security (SPADS)

Apply now >

Sensor Signal Processing

Object tracking using neuromorphic computing and Bayesian deep learning

Neuromorphic computing for 3D imaging with single-photon Lidars

Fusion of multiple sources of evidence using Bayesian chain event graphs

Advancing 3D Underwater Imaging: sensor fusion and statistical AI for enhanced robustness and interpretability

High-resolution Object Detection in the Sea Clutter Environments (SAAB Systems)

Development of spiking architectures using Bayesian deep learning

Distributed Information Fusion

Autonomy Counter-Counter Measures (Leonardo)

Robust non-linear state-space modeling: From filtering to deep learning approaches

Model based deep learning for robust multimodal 3D imaging

Pages

SPADS CDT: Sensing, Processing, and AI for Defence and Security

Search form

Pages

SPADS CDT: Sensing, Processing, and AI for Defence and Security