System and method for the automatic detection of openly-carried firearms
AssigneeCarnegie Mellon University
InventorsMarios Savvides, Chenchen Zhu, Nnamdi Adom
Life of this patent
Estimating the term…
Abstract
Disclosed herein is a system and method for the automatic detection of persons engaged in the open carry of firearms at a venue. The system and method comprise strategically placed cameras at the venue which are connected to edge devices which extract frames from video generated by the cameras. The video frames are sent to a server for analysis by an AI/ML model trained to detect firearms and, specifically, to detect persons carrying firearms. If a person wielding a firearm is detected in any image, an alert is raised and local authorities are automatically contacted. The system is designed to run continuously such as to be able to quickly detect a person in a venue carrying a firearm.
Claims9
A system for automatically detecting handheld firearms at a venue comprising:
- a server executing an object detection model trained to detect handheld firearms in one or more images of a venue and to provide a binary classification indicating the presence or non-presence of a firearm in the images;
- one or more edge devices located remotely from and in communication with the server;
- and
- one or more image sensing devices connected to each of the one or more edge devices;
- wherein each of the one or more edge devices periodically extracts still images from video provided by the one or more image sensing devices or periodically instructs the one or more image sensing devices to provide a still image;
- wherein each of the one or more edge devices periodically sends the still images to the server for submission to the object detector;
- and
- wherein the server receives the one or more still images from the one or more edge devices and inputs the received images to the object detection model.
Dependencies are inferred from the claim text.