Detecting Anomalies from Video-Sequences: a Novel Descriptor

TL;DR

This paper introduces a new descriptor based on group dynamics for detecting anomalies in crowd videos, focusing on the formation and disintegration patterns of groups over time.

Contribution

The work proposes a novel trit-based descriptor inspired by local binary patterns to analyze group behavior for anomaly detection in video sequences.

Findings

Effective detection of anomalies based on group number variations.

Performance varies with different group extraction methods.

Correlation observed between anomaly type, camera perspective, and detection success.

Abstract

We present a novel descriptor for crowd behavior analysis and anomaly detection. The goal is to measure by appropriate patterns the speed of formation and disintegration of groups in the crowd. This descriptor is inspired by the concept of one-dimensional local binary patterns: in our case, such patterns depend on the number of group observed in a time window. An appropriate measurement unit, named "trit" (trinary digit), represents three possible dynamic states of groups on a certain frame. Our hypothesis is that abrupt variations of the groups' number may be due to an anomalous event that can be accordingly detected, by translating these variations on temporal trit-based sequence of strings which are significantly different from the one describing the "no-anomaly" one. Due to the peculiarity of the rationale behind this work, relying on the number of groups, three different methods of people group's extraction are compared. Experiments are carried out on the Motion-Emotion benchmark data set. Reported results point out in which cases the trit-based measurement of group dynamics allows us to detect the anomaly. Besides the promising performance of our approach, we show how it is correlated with the anomaly typology and the camera's perspective to the crowd's flow (frontal, lateral).