Violent flows: Real-time detection of violent crowd behavior

TLDR

Surveillance video cameras are widely used, yet their effectiveness remains questionable. The study focuses on monitoring crowded events for violent outbreaks and proposes a novel real‑time detection approach. The method analyzes temporal changes in flow‑vector magnitudes, encodes them with the VIolent Flows descriptor, and classifies scenes as violent or non‑violent using a linear SVM, supported by a new real‑world surveillance dataset and benchmarks. Empirical tests show the approach outperforms state‑of‑the‑art methods, demonstrating its effectiveness.

Abstract

Although surveillance video cameras are now widely used, their effectiveness is questionable. Here, we focus on the challenging task of monitoring crowded events for outbreaks of violence. Such scenes require a human surveyor to monitor multiple video screens, presenting crowds of people in a constantly changing sea of activity, and to identify signs of breaking violence early enough to alert help. With this in mind, we propose the following contributions: (1) We describe a novel approach to real-time detection of breaking violence in crowded scenes. Our method considers statistics of how flow-vector magnitudes change over time. These statistics, collected for short frame sequences, are represented using the VIolent Flows (ViF) descriptor. ViF descriptors are then classified as either violent or non-violent using linear SVM. (2) We present a unique data set of real-world surveillance videos, along with standard benchmarks designed to test both violent/non-violent classification, as well as real-time detection accuracy. Finally, (3) we provide empirical tests, comparing our method to state-of-the-art techniques, and demonstrating its effectiveness.