SBIR Phase II: IoT System for Small Arms Detection and Response

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project lies ultimately in saving lives. This project proposes a Machine Learning-enabled Internet of Things (IoT) firearms detection system for law enforcement. Implementation of this technology would significantly reduce the cognitive burden of police officers in dangerous situations, allowing for more informed decisions. Additionally, there are benefits to the warfighter and security professionals to improve their capabilities in keeping the nation and public safe. Successful implementation and commercialization of a firearms detection system will grant capabilities to objectively monitor and leverage firearm usage data to find insights previously unknown, and to provide a data-driven approach towards real-time reactions around firearms and firearm usage. The proposed project aims to research and develop a Machine Learning-enabled, integrated IoT system dedicated to detecting and processing small arms firearm activity, such as discharges and unholsters. The challenges are two-fold: 1) to develop and iterate based on pilot user feedback regarding the hardware and software portions of the system; and 2) to employ machine learning on a unique dataset for insights on firearms knowledge and handling. The proposed research and development plan calls for pilots with several law enforcement agencies, hardware and software iterations based on user feedback, and research into a real-life dataset collected by police officers. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.