AI is getting pretty good at recognizing objects in a photo or video stream. Leading AI engines can now recognize people, cars, dogs, trees, and a whole host of objects. In cooperation with one of our retail member clients, We’ve been training an AI engine to recognize weapons: handguns, rifles, shotguns. We’re also training the engine to spot violent movements and people wearing “ski mask” baklavas, all with the intent to reduce the risk of violence and dangerous situations.
AI image detection works by submitting a large number of ‘training data’ images to a set of algorithms. By telling the AI engine which images have the target object (in this case: guns), the engine looks for patterns. When successful identifications are scored higher, the engine will tweak the variables, repeat the exercise, and after several “epochs”, the AI engine will have “learned” how to spot a gun in an image.
So far, this is fairly straightforward, with a given large set of training imagery and some computing power for the AI engine. The difficult part is to then take that image recognition and deploy it to a real-world situation.
Steps include the following:
The most difficult part of this real-world deployment is to get a reliable and consistent video feed. Working with our global client, we are standardizing on a flashable camera and edge server hardware configuration that can be deployed easily or is already onsite for other tracking purposes.
Going forward, it is our intention to make this application as widely available as possible. We are actively seeking large organizations who can help bring this application, standardized camera configurations and alert functionalities to schools, shops, churches, and campuses. If you would like to learn more, please contact us right away and let’s find a way to work together.