T4T Ammunition Data Sharing Specifications (April 2024)
This document provides guidelines and specifications for partners who wish to participate in the development of T4T’s Small Calibre Ammunition Reference Table (SMART), intended as a global reference for documentation and information exchange on illicit ammunition and the complementary ammunition detection and identification software employing computer vision artificial intelligence (CV-AI). The latter tool leverages ammunition geometry, headstamp markings, and other features to extract ammunition make, calibre, associated firearm type and, where possible, year and country of manufacture from casings. The tool should also capture and process data from seized ammunition packaging.
Partners that contribute data in the development of these tools are also invited to be beta testers and early adopters of the software. For more information, and to obtain the data sharing specifications, contact Emile LeBrun (emile.lebrun@tech4tracing.org). Credentials to privately and securely share data will be provided, as well as further information on how data is stored.
Concept ‘Benchmark Data Consortium for Explosive Ordnance Detection Algorithms’ (6 October 2023)
Since it began work to create computer vision detection algorithms for explosive ordnance objects in 2022, T4T and VFRAME have developed a robust dataset of benchmark data and video against which to test our algorithms. But we recognise that to truly validate our tools they must be tested against a wider pool of data that has not been used to create the algorithms. The same goes for all vendors that claim high-performance detection in this space. For this reason, we are proposing the establishment of a Benchmark Data Consortium for Explosive Ordnance Detection Systems, whose role will be to provide independent validation and certification of algorithm accuracy against a benchmark dataset generated by contributions from actors developing new tools, as well as EOD centres and other approved actors.
We invite other vendors, whether NGOs or for-profit companies, to participate in the Consortium, and to agree that independent verification is the only way to disprove false claims and misinformation about algorithm accuracy. With the lives of emergency service and mine action personnel on the line, the urgency to establish such a system is real.
‘Computer Vision Detection of Explosive Ordnance: A High-Performance 9N235/9N210 Cluster Submunition Detector’
Journal of Conventional Weapons Destruction, Issue 27.2, June 2023
Computer vision is a promising artificial intelligence technology that can greatly enhance humanitarian mine action (HMA) as well as support evidentiary documentation of the use of EO that are prohibited under international humanitarian law. This article describes a computer vision algorithm creation workflow developed to automate the detection of the 9N235/9N210 cluster submunition, a heavily deployed munition in the Ukraine conflict. The six-step process described here incorporates photography, photogrammetry, 3D-rendering, 3D-printing, and deep convolutional neural networks. The resulting high-performance detector can be deployed for searching and filtering images generated as part of OSINT investigations and soon, for real-time field detection objectives. The article is available here in PDF.
‘Bringing New Tech to Arms Control: T4T Report from UN PoA BMS8’
T4T Policy Brief No. 1, August 2022
T4T’s first Policy Brief provides a summary of the T4T side event at the Eighth Biennial Meeting of States to consider implementation of the UN Programme of Action on Small Arms and Light Weapons and the International Tracing Instrument (ITI) in June 2022. Hosted by the Permanent Missions of Belgium and Mexico to the United Nations, the event provided perspectives for the inclusion of new technology-based approaches to arms and ammunition control and showcased two specific emerging technologies: computer vision for the automated detection of arms and ammunition items, and machine learning techniques for recognising, cataloguing, and sharing data extracted from firearms and ammunition. These technologies offer opportunities to enhance a range of arms and ammunition control processes, including for diversion prevention; supply chain monitoring; arms and ammunition identification and tracing in conflict and crime contexts; peacekeeping intelligence; investigations into human rights abuses and international humanitarian law (IHL) violations; among other initiatives and processes.
T4T Statement at Third Substantive Session of the UN Open-ended Working Group on Conventional Ammunition, 14 February 2023
Statement by Robert Sim, Director of Research, Tech for Tracing
T4T Statement at Second Substantive Session of the UN Open-ended Working Group on Conventional Ammunition, 17 August 2022
Statement by Chris Gough, Technical Director, Tech 4 Tracing
T4T Statement at UN PoA BMS8, 29 June 2022
Statement by Tech 4 Tracing
T4T Statement at First Substantive Session of the UN Open-ended Working Group on Conventional Ammunition, 25 May 2022
Statement by Robert Sim, Research Director, Tech 4 Tracing