Multi-camera CCTV software for the Mac
Features — Smart motion detection powered by AI
SecuritySpy uses deep neural networks for computer vision, in order to accurately detect humans and vehicles. These networks have been trained using hundreds of thousands of real CCTV images, in order to produce highly accurate classification.
By using neural networks, false-positive detections (for example, a trigger caused by a swaying tree), can be dramatically reduced or even eliminated.
All analysis is done locally on your Mac; images are not sent to any Internet server for processing. This protects your privacy, and allows for high performance and low latency.
Here's how it works:
|Standard motion detection is performed on the incoming video in order to locate areas of motion. This is done by comparing pixel values in the current frame with those in previous frames.|
|When motion is detected, the image is cropped to just the area of motion, and scaled to a size that can be accepted by the neural network.|
|The cropped image is passed to the neural network for classification.
The neural network outputs prediction probabilities, indicating how certain it is that the image contains either a human or a vehicle.
|If the certainty level exceeds a user-defined threshold, recording and/or notifications can be triggered.
You decide how this information is used to trigger various functions of the software: for example, you can set SecuritySpy to record all motion, but only generate notifications when a human is detected.