Congratulations to Cohort 3 Rep James Walsh, co-author for the article on The Computer Journal, Near Real-Time Social Distance Estimation In London, which won the Wilkes Award, a prestigious commendation given annually to the authors of the best paper published in the volume of The Computer Journal in terms of contribution to the field, based on criteria including: technical quality; knowledge of field; rigour of arguments; originality; clarity of presentation; standard of English; references to other work. See https://academic.oup.com/comjnl/pages/Wilkes_award
“We are thrilled to be honoured with this award. This achievement not only recognizes our efforts but also highlights the impact we strived to make during the COVID pandemic. Amidst the uncertainty of that time, our project's success is owed to the resourcefulness of our team, leadership of our research group, and the collaborative partnership with the Greater London Authority.” - James Walsh, FIBE2 PhD student
During the COVID-19 pandemic, a new monitoring tool developed under Project Odysseus was used in London to help improve public health. This tool used advanced computer technology and offered near real-time data on how well people were following social distancing rules in London over an 18-month period including the lockdowns in 2020 and 2021. It played a big role in informing over 700 social distancing measures during the first wave of the pandemic.
Locations of JamCams run by Transport for London
Professor Mark Girolami, Chief Scientist at The Alan Turing Institute and a leading figure in civil engineering at Cambridge, led the project together with researchers from Cambridge and Warwick universities. He was assisted by Cambridge Engineering alumni Andrew Wang and Mihai Ilas, who worked on the project as interns. FIBE2 PhD students James Walsh from Cohort 3 and Yannis Zachos from Cohort 2 were part of the team who developed and provided this tool to London authorities, including the Greater London Authority (GLA) and Transport for London (TfL).
“The Cambridge Engineering students that joined The Turing team made important innovative contributions to the overall system that was deployed, ensuring its efficient operation.” - Professor Mark Girolami
The number of buses, cars, motorbikes, people and trucks detected by the image processing algorithms.
Project Odysseus used live feeds from over 900 traffic cameras to monitor vehicles and pedestrians. "Digital Twins," which are realistic digital models of physical spaces, along with advanced computer algorithms calculated the distances between people, using low-resolution footage to ensure privacy. The project repurposed tools and data from the London Air Quality monitoring study to also track pedestrian activity and acted as an "early warning system," giving near real-time insights into the impact of their actions to help policymakers understand how well the two-meter COVID-19 rule was working. It also quickly identified areas where changes were needed, such as moving bus stops, widening sidewalks, and closing parking spaces to ensure people could maintain social distancing. These findings were published in The Computer Journal.
Looking ahead, the team plans to improve the early warning system. With the transparent and practical uses of machine learning applications to enhance the accuracy of the Digital Twin, and provide more user-friendly recommendations for policymakers.
Reference:
James Walsh; Oluwafunmilola Kesa; Andrew Wang; Mihai Ilas; Patrick O’Hara; Oscar Giles; Neil Dhir; Mark Girolami; Theodoros Damoulas. ‘Near Real-Time Social Distance Estimation In London’. The Computer Journal (2023). DOI: 10.1093/comjnl/bxac160
Project Odysseus – Understanding London ‘busyness’ and exiting lockdown | The Alan Turing Institute