Gun in Hand Detection
What it does. Where it can be used: height, distance, angle of view. Chained Classifications.
Book a Demo
Gun in Hand Detection In Internal Testing
What it does:
Determines if the object in a person’s hand is a gun. Includes handguns, revolvers, long guns / rifles, pistols, and portable machine guns.
Allows you to create alerts, filter event feeds and 24/7 views based on the presence of a gun in a person's hand(s).
Best Practices:
Prerequisite:
Requires person detection and all of their camera placement requirements.
Camera Distance Requirements
This model looks for objects in people’s hands, and thus does not work when the object is shielded by a body. As it is often looking at a much smaller object, which still needs to be 20x20 or larger, the person must be rather close to the camera.
Consensus Based Architecture In Development Expected in Q4
The person detection model runs currently on local level and was created by Survail. By the end of Q4, two gun detection double checks, with a model created by Intel and another by a third-party, should be implemented. Here's an example of the Intel model:
Legal Limitations
Enabling Gun Detection requires its own EULA that limits our liability. Gun detection is obviously not the single and only method you should have of protecting your institution. Heavily modified, concealed, and partially hidden weapons will NOT be detected. Gun in hand detections will NOT differentiate between real and toy guns.