General AI technology can recognize objects in a photo or video stream. Leading AI engines can recognize people, cars, dogs, trees, etc. We have been training an AI engine to recognize weapons (e.g., handguns, rifles, shotguns,) violent movements, and people wearing “ski mask” baklavas, thanks to the collaboration with one of our retail clients. Our intention is to significantly reduce the risk of violence and danger.
The code for this Weapons Detection AI is now FREELY AVAILABLE AND OPEN SOURCE. Click here for Github.
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 will look 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, using a large set of training images and some computing power for the AI engine has been reasonably straightforward. The tricky part is taking the image recognition and deploying it to a real-world situation.
The steps for this are as follows:
The most challenging part of the real-world deployment is getting a reliable and consistent video feed. Working with our global client, we are standardizing flash camera use and edge server hardware configuration that can be deployed easily or is already onsite for other tracking purposes.
The code for this Weapons Detection AI is now FREELY AVAILABLE AND OPEN SOURCE. Click here for Github.
Client:
Convenience Chain
Goal:
Enhance Safety
Development Time:
Ongoing Training
Deployment:
Undisclosed