Definition
Flagging events that deviate from normal patterns — a fall, an intrusion, a defect — without a labelled example of every possible problem.
Anomaly detection learns what 'normal' looks like and raises an alert when footage departs from it, which suits surveillance and quality control where the failures are rare and varied. It trades precise labels for the ability to catch the unexpected.
Also known as
anomaly detection algorithms, outlier detection
Specialist software house for video, real-time and AI products. Founded 2005. 50 in-house engineers.
