A generic framework for video understanding applied to group behavior recognition

TL;DR

This paper introduces a comprehensive framework for video understanding that detects, tracks, and recognizes group behaviors in surveillance videos, utilizing clustering and a formal event language, validated across multiple real-world datasets.

Contribution

It proposes a novel generic framework combining detection, tracking, clustering, and formal event description for group behavior recognition in videos.

Findings

Successfully validated on 4 camera views from 3 datasets

Effective clustering of trajectories using Mean-Shift algorithm

Accurate recognition of group behaviors in diverse environments

Abstract

This paper presents an approach to detect and track groups of people in video-surveillance applications, and to automatically recognize their behavior. This method keeps track of individuals moving together by maintaining a spacial and temporal group coherence. First, people are individually detected and tracked. Second, their trajectories are analyzed over a temporal window and clustered using the Mean-Shift algorithm. A coherence value describes how well a set of people can be described as a group. Furthermore, we propose a formal event description language. The group events recognition approach is successfully validated on 4 camera views from 3 datasets: an airport, a subway, a shopping center corridor and an entrance hall.