{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/b0dfe65892e144fca0692565c52969a4\" frameborder=\"0\" width=\"1660\" height=\"1245\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1245,"width":1660,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1245,"thumbnail_width":1660,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/b0dfe65892e144fca0692565c52969a4-0d6185224ea60e03.gif","duration":477.6,"title":"AirSecure : Drone and CCTV Security Monitoring System","description":"This Loom presents Airsecure, a drone-aware enterprise security monitoring system that unifies drones, CCTV, and incident workflows. It describes a core pipeline using OpenCV background subtraction and object detection, plus BLIP-style captioning and a severity risk engine to classify activities like loitering, perimeter entry, night movement, and unknown vehicle presence. The demo shows a Streamlit UI that processes uploaded videos by detecting scenario details, generating alerts, saving logs in SQLiteDB, and using ChromaDB embeddings for search questions such as how many people were detected and whether one person moved across frames. High-severity alerts trigger Telegram notifications with images, demonstrated for a person at a main gate and a restricted-area entry."}