Memento SafeEdge Guardian - AI Child Safety Monitoring for Home Danger Zones

The Memento SafeEdge Guardian operates as a real-time computer vision system designed to monitor restricted home zones, such as staircases, balconies, and windows. At the core of the system is the Adafruit Memento programmable camera, which captures high-definition video frames of the monitored area. These video frames are streamed directly to the Raspberry Pi 5. The Raspberry Pi 5 acts as the central processing unit, executing a 64-bit Raspberry Pi OS environment running Python and OpenCV. Inside this software pipeline, a specialized YOLO (You Only Look Once) object detection model analyzes the incoming video stream frame by frame. The YOLO model is trained to recognize human figures, specifically distinguishing children within the camera's field of view. When the system detects a child entering a predefined danger zone boundary within the frame, it triggers immediate logic outputs. This can include executing a local Flask-based web server application to log events or display real-time status alerts. Simultaneously, the system can interface with a connected NeoPixel LED ring, utilizing its eight individually addressable RGB LEDs to provide visual warning cues, shifting colors or flashing to signal an active safety alert to anyone nearby.