AI-Driven Real-time Image Processing for Enhanced Perception and Safety in Autonomous Vehicles

About the Project

Summary of the proposed research:

Autonomous vehicles rely heavily on accurate, real-time perception of their surroundings to ensure safe navigation and effective decision-making. However, challenges remain in reliably detecting objects, understanding scenes, and reacting appropriately in diverse and dynamic environments – particularly under adverse conditions such as low light, fog, heavy rain, or high traffic density. This PhD project addresses these limitations by proposing a novel AI-driven image processing framework that enhances the perception capabilities of autonomous vehicles while maintaining real-time performance on low-power, embedded systems.

The aim of the project is to design and implement an advanced real-time image processing system using AI to improve the perception, environmental awareness, and safety of autonomous vehicles, particularly in challenging and resource-constrained conditions.

The specific objectives of the project are to:

• Design and develop advanced perception models using deep learning techniques to support key tasks such as object recognition and environmental understanding in autonomous systems.
• Investigate and implement multi-sensor fusion strategies to improve scene interpretation and reduce perceptual uncertainty.
• Explore image enhancement approaches to improve visual clarity and perception reliability in challenging environmental conditions, such as low visibility or noise interference.
• Optimise AI algorithms for deployment in resource-constrained environments, focusing on real-time performance, computational efficiency, and energy-aware processing.
• Apply adaptive learning methods to improve autonomous decision-making in dynamic and unpredictable scenarios, with an emphasis on safety and efficiency.
• Conduct a comprehensive evaluation of the system under diverse conditions to validate its reliability, efficiency, and real-world applicability

How to apply:

For further information please contact: Dr Anas Amjad at a.amjad@staffs.ac.uk

The applications should consist of a cover letter or personal statement of interest, and a CV.

Dr Anas Amjad

Course Director – Electrical and Electronic Engineering

School of Digital, Technology, Innovation & Business

University of Staffordshire

College Road

Stoke-on-Trent

ST4 2DE

The expected start dates are January and April 2026.

Entry Requirements:

Applicants should have a First- or Upper Second-Class UK honours degree, or equivalent, in a relevant discipline such Artificial Intelligence, Electronic Engineering, Electrical and Electronic Engineering, Robotics, Mechatronics. An MSc with Distinction or Merit in a relevant subject is highly desirable.

A strong background in AI, Computer Vision, Deep Learning, or Autonomous Systems is required, with experience in Python and deep learning frameworks such as TensorFlow or PyTorch for real-time image processing. Familiarity with LiDAR-Camera fusion, Edge AI optimisation, and reinforcement learning would be highly beneficial, as the research involves developing advanced perception models for autonomous vehicles, integrating multi-sensor data, and optimising AI algorithms for efficient deployment on embedded hardware.

The standard minimum IELTS Academic requirement is 6.5 overall with no less than 6.0 in each band. Some International students are also required to meet UKVI requirements for the appropriate study visa. A valid ATAS certificate (where required) must be secured as a prerequisite to enrolment.