What anomaly detection is (learns 'normal', flags deviation — no rule authored) and how it differs from rule-based behavioral analytics; the four model families (reconstruction/prediction autoencoders, one-class, weakly-supervised MIL, and 2025-2026 vision-language methods — model internals owned by the AI section); the honest accuracy story (controlled benchmarks ~96-98% AUC, real-world UCF-Crime ~80-88% AUC, never 100%); the false-alarm/base-rate math (~86,400 scored moments/day, ~10 real anom
Download free PDF
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
This reference explains anomaly detection in surveillance video, the four model families, realistic accuracy and the base-rate math behind false alarms. Our seven-volume handbook covers the full video stack; start with Volume 6 for detection, tracking and video search, then Volume 7 for production serving and regulation, and Volume 1 for encoding. Written by Nikolay Sapunov, CEO at Fora Soft.
Expecting anomaly detection to flag incidents without flooding operators with false alarms?
Send us sample footage and alert volumes, and we will estimate real accuracy on your scenes and the false-alarm rate operators will see. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
