Robust Real-Time Unusual Event Detection using Multiple Fixed-Location Monitors

TLDR

The paper proposes a novel algorithm for detecting certain types of unusual events. The algorithm uses multiple fixed‑location monitors that collect low‑level statistics, generate alerts on unusual measurements, and fuse these alerts into a final decision, and was evaluated on real crowded scenes with ground‑truth to report detection and false‑alarm rates. The algorithm meets key deployment requirements, requiring only a few minutes for minimal setup, operating fully automatically, remaining robust in crowded scenes without tracking, achieving effectiveness after a few minutes of routine observation, and running in real time.

Abstract

We present a novel algorithm for detection of certain types of unusual events. The algorithm is based on multiple local monitors which collect low-level statistics. Each local monitor produces an alert if its current measurement is unusual, and these alerts are integrated to a final decision regarding the existence of an unusual event. Our algorithm satisfies a set of requirements that are critical for successful deployment of any large-scale surveillance system. In particular it requires a minimal setup (taking only a few minutes) and is fully automatic afterwards. Since it is not based on objects' tracks, it is robust and works well in crowded scenes where tracking-based algorithms are likely to fail. The algorithm is effective as soon as sufficeint low-level observations representing the routine activity have been collected, which usually happens after a few minutes. Our algorithm runs in realtime. It was tested on a variety of real-life crowded scenes. A ground-truth was extracted for these scenes, with respect to which detection and false-alarm rates are reported.