Mock up scene of paramedics pushing patient into ambulance vehicle

PACE-AI: The Pedestrian Collision Forensics Evaluator from Coventry University

Funder

Coventry University

Project Team

PI: Dr Christophe Bastien, Coventry University
Vadhiraj Shrinivas, Coventry University
Dr Huw Davies, Coventry University
Albi Lamaj, IP Associate Director and Technology Transfer, Enterprise Innovation Organisation, Coventry University
Dr Alireza Daneshkhah, Emirates Aviation University
Prof Joseph Hardwicke, UHCW

Collaborators

Lead: Coventry University
Partner: University Hospitals Coventry and Warwickshire (UHCW)

Duration

January 2018 - Present

Project Overview

Every year, thousands of pedestrians suffer life altering injuries or lose their lives in traffic accidents. The aftermath is often chaotic with investigations hampered by limited information and hit and run cases going unsolved. But what if there was a way to instantly reconstruct these accidents, providing crucial evidence and bringing justice to victims?

Enter PACE-AI, a revolutionary web-based technology developed by Coventry University. This cutting-edge tool uses artificial intelligence to analyse accident scenes with unprecedented speed and accuracy. A simple data input of basic information about the vehicle and the pedestrian, PACE-AI can determine the vehicle’s speed, the pedestrians crossing speed and even the direction of travel. This information is invaluable to the police investigations, emergency medical response and even vehicle safety design.

PACE-AI will require an estimate of the bumper and windscreen damage locations, the pedestrian height and weight, a search tolerance for the head impact strike on the windscreen and… that is it. PACE-AI will calculate, in seconds, all the plausible combinations that can lead to this collision and will provide to the forensics’ team the vehicle impact speed, pedestrian crossing speed, and pedestrian.

Verified by real-world data, PACE-AI provides detectives with crucial information from the start of the investigation, reducing the collision design domain, as well as solving complex hit-and-run cases.

Project Objectives

The idea is to create intelligent decision support tools, easy to use, non-expert driven, working in situ, which is capable in seconds to:

Solve forensic pedestrian collisions, including hit-and -run cases, hence supporting the justice process, speeding up investigations, reducing Police forensic costs and maximise Police Force usage.
This tool is now available and can:
- Provide ES with a tool able to provide accurate triage to reduce pedestrian road deaths, improve and speed up their recovery, hence freeing up NHS resources (tool under development)
- Provide automotive manufacturers and legislative bodies with tools to design safer vehicles.

Impact Statement

Our PACE-AI method is only using vehicle shape and pedestrian anthropometry. It can extract, in seconds, not only the vehicle impact speed (which takes the Police days), but also the pedestrian crossing speed, gait and crossing direction (impossible using Searle). As PACE-AI has an embedded patented convergence algorithm based on AI, which has been trained using 3000 computer cases, it can converge to the right solution in seconds. In hit-and-run cases, if the vehicle is recovered, it is possible to explain how the collision took place, which no other method can do. Thanks to its user-friendly interface, PACE-AI can be used by non-experts. PACE-AI can have a great impact on the coronal process and make our society a safer place. We are happy to give a demonstration of PACE-AI, as well as discuss collaborations.

Enquiries about accessing PACE-AI can be made to pedestrian-collision@coventry.ac.uk or christophe.bastien@coventry.ac.uk.

Outputs

Patent: Application number: (GB)2313779.7

Trademark: Trademark Protection: In the United Kingdom

Trademark Number: No. 4080416 PACE-AI in Class(es) 9, 42, 45 under the ownership of Coventry University

Bastien, C., Sturgess, C. N., Davies, H., Wellings, R., Bonsor, J., & Cheng, X. (2024). A Proof of Concept Model to Calculate White and Grey Matter AIS Injuries in Pedestrian Collisions. Computer Methods in Biomechanics and Biomedical Engineering, 27(11), 1563-1585. Article 240542684. https://doi.org/10.1080/10255842.2024.2368658
Shrinivas, V., Bastien, C., Davies, H., Daneshkhah, A., Hardwicke, J., Neal-Sturgess, C. E., & Lamaj, A. (2024). Integrating Machine Learning in Pedestrian Forensics: A Comprehensive Tool for Analysing Pedestrian Collisions. SAE Technical Papers, Article 2024-01-2468. https://doi.org/10.4271/2024-01-2468
Bastien, C., Neal-Sturgess, C. E., Panno, R., Shrinivas, V., & Scatina, A. (2023). A Peak Virtual Power Concept to Compute Brain Injuries Associated with Concussion. Journal of Head Neck & Spine Surgery, 5(1). Advance online publication. https://doi.org/10.19080/JHNSS.2023.05.555651
Shrinivas, V., Bastien, C., Daneshkhah, A., Davies, H., & Hardwicke, J. (2023). Parameters influencing pedestrian injury and severity: A systematic review and meta-analysis. Transportation Engineering, 11, Article 100158. https://doi.org/10.1016/j.treng.2022.100158
Bastien, C., Sturgess, C. N., Davies, H., Hardwicke, J., Cloake, T., & Zioupos, P. (2021). A Generic Brain Trauma Computer Framework to Assess Brain Injury Severity and Bridging Vein Rupture in Traumatic Falls. Journal of Head Neck & Spine Surgery, 4(4), 47-60. Advance online publication. https://doi.org/10.19080/jhnss.2021.04.555641
Bastien, C., Sturgess, C. N., Davies, H., & Cheng, X. (2020). Computing Brain White and Grey Matter Injury Severity in a Traumatic Fall. Mathematical and Computational Applications, 25(3), Article 61. https://doi.org/10.3390/mca25030061
Rubrecht, B., Bastien, C., Davies, H., Wellings, R., & Burnett, B. (2019). Numerical Validation of the Pedestrian Crossing Speed Calculator (PCSC) using Finite Element Simulations. Global Journal of Forensic Science & Medicine, 1(4), Article GJFSM-19-RA-525. https://irispublishers.com/gjfsm/pdf/GJFSM.MS.ID.000525.pdf
Bastien, C., Wellings, R., & Burnett, B. (2018). An Evidence Based Method to Calculate Pedestrian Crossing Speeds in Vehicle Collisions. Accident Analysis & Prevention, 118, 66-76. https://doi.org/10.1016/j.aap.2018.05.020