As Editor-in-Chief of The Computer Journal, published by Oxford University Press on behalf of BCS, The Chartered Institute for IT, it is my honour to select the recipient of the annual Wilkes Award, awarded to the authors of the best paper published in the previous year’s volume. The key judging criteria for the Award are originality and quality of theme and treatment, as assessed by an expert judging panel.
We are pleased to announce this year’s winning and runner-up papers for the 2024 Wilkes Award for Volumes 66-67 (2023-2024):
Winning paper
Near Real-Time Social Distance Estimation In London
James Walsh, Oluwafunmilola Kesa, Andrew Wang, Mihai Ilas, Patrick O’Hara, Oscar Giles, Neil Dhir, Mark Girolami and Theodoros Damoulas
The Computer Journal, Volume 67, Issue 1 (January 2024), pp.95-109
https://doi.org/10.1093/comjnl/bxac160
This paper describes a computer vision and machine learning system built by the Alan Turing Institute to estimate social distancing adherence across London during the COVID-19 pandemic, repurposing infrastructure originally developed for an air quality monitoring platform. The system processes footage from over 900 public traffic cameras in near real time. A calibration stage learns a mapping from each camera’s pixel coordinates to real-world locations using vanishing-point estimation and manually identified landmarks such as road markings and traffic lights, while a separately tuned object detection model locates pedestrians within each frame. From these calibrated detections the authors derive social distancing and group-clustering metrics, and add a change-point detection process to flag cameras whose calibration has drifted due to weather, vegetation growth or physical disturbance. Over an 18-month deployment the platform processed more than 19 terabytes of footage, and the paper reports that Transport for London used its output to justify and evaluate over 700 street-level interventions, such as widened pavements and relocated bus stops, with the authors presenting before-and-after distancing measurements for several specific interventions as evidence of effect. It is a paper less about a single novel algorithm than about the disciplined engineering, calibration and validation needed to turn computer vision into a trustworthy, continuously operating policy tool, and the documented real-world impact on London’s pandemic response made it a clear and worthy winner.
Runner-up
GUI: A Geolocation Method for Unreachable IP
Shuodi Zu, Xiangyang Luo, Liang Wang and Fan Zhang
The Computer Journal, Volume 67, Issue 5 (May 2024), pp.1963-1978
https://doi.org/10.1093/comjnl/bxad116
The runner-up paper tackles a practical limitation in IP geolocation: many devices on the internet do not respond to the network probes that existing tools rely on, whether for security reasons or to save resources, and previous methods could either not geolocate such targets at all or could only place them at city level. The authors propose GUI, which first determines a target’s city by comparing its partial detection path against a metropolitan-area network topology built from many landmark devices with known locations, then refines this to a more precise estimate either by finding landmarks that share the target’s subnet, or, failing that, by tracing back to the nearest shared router and using the landmarks reachable from it. Tested across 15 cities in China and the USA, where the authors find that more than a third, and in several cities well over half, of sampled IPs are unreachable to standard probing, GUI substantially outperforms existing methods and commercial geolocation databases on both city-level success rate and the precision of within-city location estimates for these previously hard-to-locate targets.
You can browse previous winners of the Wilkes Award, and find out more about the Award itself. Thank you also to the 2024 Wilkes Award judging panel:
- Professor Alastair Irons, Abertay University, UK
- Professor Alan Marshall, University of Liverpool, UK
- Professor Chris Mitchell, Royal Holloway, University of London, UK
- Professor Jim Woodcock, University of York, UK
The award is named after Sir Maurice Wilkes (1913-2010), Director of the Cambridge University Computer Laboratory from 1945 to 1980, throughout the development of stored program computers starting with EDSAC, which ran the first realistic programs on a stored-program electronic computer in 1949. He went on to invent microprogramming, and, with David Wheeler and Stanley Gill, developed an early programming system based on subroutines and labels that shaped how software was written for decades afterwards. Wilkes was also the founding President of the British Computer Society (1957-60), received the ACM A.M. Turing Award in 1967, and was knighted for his services to computing in 2000.
Digital Society & Policy 