Real-Time Moving Flock Detection in Pedestrian Trajectories Using Sequential Deep Learning Models

The analysis of pedestrian trajectories has become an essential aspect of understanding human mobility patterns in various environments such as urban spaces, transportation systems, and public gatherings. In particular, the identification of pedestrian groups or "flocks" moving together in real-time is a challenging but crucial task. A flock can be defined as a group of individuals whose movements are highly correlated over time, often indicating a shared goal or destination. Detecting such flocks is not only important for crowd management and safety but also for enhancing the effectiveness of autonomous systems, such as self-driving cars, and improving human-robot interaction. Collective motion in trajectory data can be categorized into different formats, including flocks, convoys, and swarms [1]. A flock is a set of agents moving together within a limited spatial region over a specific time interval. A convoy extends this definition by maintaining the same group structure over longer periods, making it more stable in dynamic environments. A swarm represents a more loosely connected group, where individuals exhibit similar movement patterns but do not necessarily maintain fixed spatial relationships. In this study, we focus on moving flock detection, where groups of pedestrians dynamically form and dissolve while moving together over short time intervals.