A research team from the University of Leicester have developed the OPTIMUS prototype using AI to track the human brain’s ability to track and process hazards.
Tracking the eye movement of participants
The brain’s ability to track and process hazards will be set against an inventive artificial intelligence (AI) tool in a novel interdisciplinary research study conducted by University of Leicester (UL) scientists.
Researchers in the School of Computing and Mathematical Sciences have collaborated with visual perception experts from UL’s Department of Neuroscience, Psychology, and Behaviour to outline the study, which will track the eye movements of each participant when confronted with multiple fast-moving hazards instantaneously.
It is intended for this research to contribute toward the development of a next-generation rail safety device, which is currently being created as part of an Innovate UK Knowledge Transfer Partnership (KTP) between Leicester experts and systems engineering specialists Synoptix.
The OPTIMUS prototype: Machine learning and an AI-based object detection system
The OPTIMUS prototype was initially installed at a Network Rail-operated level crossing near Cheltenham earlier this year. The technology utilises machine learning and an AI-based object detection system – which is hosted locally on the small edge-based device – to recognise and calculate various types of traffic.
It has been noted that this novel interdisciplinary aspect of the project means that researchers can compare both accuracy and speed of detection capability to a human completing the same task. It is assumed that this study is the first to compare humans and AI for the task of ‘visual census’ in this way.
“The question was asked on the project ‘How good is good?’ in relation to the performance of the OPTIMUS system at the crossing,” explained George Leete, KTP Research Associate within the Artificial Intelligence, Data Analytics, and Modelling (AIDAM) Centre at UL, and leader of the development of the machine learning aspect of the project.
“I am confident that the results of this study will lend us some valuable insight into this question, firstly how good humans are at the current task, and secondly whether our current system holds up to human standards. We believe this is the first time an AI-based system will be validated against a standard in this way, opening the door for other systems to be validated via a similar method.”
Comparing AI and human performance to understand the human brain
Dr David Souto, Dr Doug Barrett and Dr Claire Hutchinson make up the team of Leicester psychologists lending their expertise to the study.
“We are really excited to be involved in this interdisciplinary work. Comparing AI and human performance in this way will help us understand how the human brain identifies and weights visual information so that we can safely navigate the world around us,” said Dr Claire Hutchinson, Associate Professor in Experimental Psychology at UL.
“Synoptix is delighted to have the opportunity to work with both Leicester’s School of Computing and Mathematical Sciences and the Department of Neuroscience, Psychology and Behaviour on this breakthrough study,” added Stephen Measures, Project Lead at Synoptix.
“The results of this will be crucial to help our project team validate the performance and effectiveness of the OPTIMUS prototype system and its AI model when compared to a human-based approach to object census.”
“We feel very privileged to be part of this collegiate working group as we seek to push the boundaries of this project which has the potential to be a market leader in AI and data analytics; not only will it have a huge impact on AI technologies, but it has real significance in being a fully interactive element to increase safety across Network Rail’s infrastructure,” concluded Justin Mountjoy, Programmes Director at Synoptix.
Contributing to pedestrian safety
According to Network Rail, which is responsible for the country’s rail infrastructure, there are approximately 6,000 level crossings in the UK. Figures for 2019 to 2020 demonstrate that there were 316 near misses with pedestrians on UK level crossings and two pedestrian fatalities.
The OPTIMUS prototype was installed at a site on the cross-country route in January 2022 and has identified hundreds of thousands of movements on the crossing, including pedestrians, cyclists, and other road traffic. As the detection and classification of users occur locally on the device – and the only data conveyed is of traffic numbers and types – the privacy of crossing users is protected in line with data protection guidelines.
Synoptix provides multi-disciplinary systems, including engineering support, across various technical industries. The organisation is certified by the Railway Industry Supplier Qualification Scheme (RISQS) for the provision of Systems and Safety Engineering Consultancy to the Rail Industry. The KTP is funded by Innovate UK.