Anomaly detection looks for the unusual without a pre-written rule for it. Instead of "alert when someone crosses this line", it learns what normal looks like for a scene and flags departures from that pattern — a person where people are never seen, a sudden scattering of a crowd, motion at an odd hour. This is its appeal over rule-based analytics: it can surface events nobody thought to define in advance.
The approaches range from models that learn normal and measure reconstruction error, through weakly-supervised methods trained on labelled "event/no-event" video, to recent vision-language methods that describe a scene and reason about whether it is odd. Accuracy is the catch: controlled benchmarks reach roughly 96–98% AUC, but on realistic, messy datasets (such as UCF-Crime) performance falls to about 81–88% AUC. Combined with how rare true anomalies are, this creates a base-rate trap — at a 1% false-positive rate a busy camera can produce hundreds of false flags for every genuine one.
Two consequences follow. First, deploy anomaly detection as triage that directs human attention, not as an autonomous alarm — the false-positive volume makes unattended alerting unworkable. Second, the ONVIF catch: anomaly is not one of the normative ONVIF rule types (only line, field, loitering, and counting are), so it travels as vendor-defined Profile M metadata and is more SDK-locked than rule-based analytics. It is personal data and generally not Article 9 biometric, but is often EU AI Act high-risk. The model internals belong to the AI for Video Engineering section.
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
Anomaly detection catches events no one wrote a rule for, and its value depends on tuning false alarms down to a level operators will trust. We wrote seven volumes covering the whole video stack, and for anomaly detection start with Volume 6: computer vision models, detection and tracking, the AI feature lifecycle and deployment topologies. Written by Nikolay Sapunov, CEO at Fora Soft.
Rolling out anomaly detection without flooding operators with false alarms?
Share sample footage and alert goals and we will deliver an anomaly detection plan with model approach, tuning targets and a pilot design to measure false alarm rates. 250+ video products shipped since 2005.
