Real-Time Weapon Detection Using AI and IoT: A Case Study

• Analytics & Modeling - Machine Learning
• Cybersecurity & Privacy - Intrusion Detection

• Education
• National Security & Defense

• Product Research & Development

• Computer Vision
• Tamper Detection

• Cloud Planning, Design & Implementation Services
• System Integration

The Customer, a pioneer in Autonomous Systems, was faced with the challenge of migrating its computer vision cloud platform to the Amazon cloud within a four-month timeframe. The migration was necessary to enable the platform to perform highly scalable, real-time weapon detection to identify firearms and suspects in high-security environments. The goal was to provide security and safety to essential businesses, communities, and schools through real-time human behavior recognition and weapon detection technologies, enabled by AI & Machine Learning. The Customer was also looking to protect communities by bringing AI-driven visual imaging and human behavior recognition technology to every school, public building, and business across the country. They wanted to develop a weapon detection solution that they could integrate with their apps in the AWS cloud, to be able to deter, detect, and defend against shooters quickly and efficiently.

The Customer is a world-renowned pioneer in Autonomous Systems. Their goal is to provide security and safety to essential businesses, communities, and schools through real-time human behavior recognition and weapon detection technologies, enabled by AI & Machine Learning. They are committed to protecting communities by bringing AI-driven visual imaging and human behavior recognition technology to every school, public building, and business across the country. They are currently working on numerous government and large-scale commercial projects and continue to evolve their weapon detection solution to meet the security and safety challenges of the future.

Provectus and the Customer’s engineering teams collaborated to design a sustainable solution on AWS that would meet the demands of processing multiple security camera feeds in real-time. The solution involved deploying proprietary ML models on Amazon SageMaker, applying DevOps best practices, rolling out a video decode engine, swapping in Customer’s new UI, and integrating an IoT alert system with Alexa notifications. Provectus’ first goal was to deploy ML inferencing pipeline on AWS in such a manner to minimize the round-trip latency and improve the performance of ML models on 30 fps video streams. They also incorporated gun detection alerts sent to the Alexa device. Thanks to real-time data streaming and processing, onboarded clients receive security alerts instantly via SMS, email, and Alexa and have more time for response. Finally, Provectus implemented a custom UI with an interactive timeline, allowing to easily create cameras and users in the admin board, custom bins, a favorites tagging system, and notifications and alerts.

• The Customer received a highly scalable, real-time, multi-tenant, production-grade weapon detection solution for video processing with AI in just four months. The platform is capable of detecting weapons in multiple, simultaneous security video streams with an accuracy of 99% and a time to detection of 15ms. The solution also includes a custom UI with an interactive timeline, allowing for easy creation of cameras and users in the admin board, custom bins, a favorites tagging system, and notifications and alerts. This has resulted in a user-friendly design that is easy to use for onboarded clients and simple to maintain for the admins. The integration of an IoT alert system with Alexa notifications ensures that onboarded clients receive security alerts instantly via SMS, email, and Alexa, providing them with more time to respond to potential threats.

• 99% detection accuracy

• 15ms time to detection

• Solution was delivered in 4 months