00:00:00/Glossary
Video intelligence
Video intelligence is the use of AI to extract meaning from video, the people, actions and events in the footage, rather than just recording and storing it. Instead of a pile of hours to scrub through, the footage becomes something you can question: what happened, when, and involving whom.
From recording to understanding
Cameras have always been good at capturing and terrible at explaining. A recording system can tell you it holds two hundred hours of footage; an intelligent one can tell you what happened in them. Video intelligence is that shift. A vision model describes what's happening in every frame (people, objects, actions, hazards), with no training on your site and no tagging, so the footage can be searched, monitored and summarised instead of merely replayed.
Video intelligence vs video analytics
Video analytics is the older, narrower term, built around motion detection, line crossing and object counting. Video intelligence is the umbrella it now sits under, covering everything from those classic triggers to vision models that describe a whole scene in language. The short version: analytics answers “did something move”, intelligence answers “what happened”.
What a video intelligence platform does
It reads frames from the cameras a site already has, describes what's happening, and turns those descriptions into plain-English search, alerts and daily reports. Type “person in a red jacket near the till” and the answer comes back in seconds. Svid calls itself the video intelligence platform, and the output of the process is searchable video: footage that can be read rather than watched.
Related footage
Glossary
Video analytics
Video analytics is the automated analysis of video by software, traditionally to detect motion, count objects or flag events like a line being crossed.
Glossary
Searchable video
Searchable video is footage an AI has described frame by frame, so you can query it in plain English. It's also what Svid stands for: Searchable Video.
Glossary
Natural language video search
Natural language video search finds moments in footage from a typed description, like “person in a red jacket near the till”, with no scrubbing or timestamps.