Data-Driven Motion Pattern Segmentation in a Crowded Environments

Motion is a strong clue for unsupervised grouping of individuals in a crowded environment. We show that collective motion in the crowd can be discovered by temporal analysis of points trajectories. First k-NN graph is constructed to represent the topological structure of point trajectories detected in crowd. Then the data-driven graph segmentation and clustering helps to reveal the interaction of individuals even when mixed motion is presented in data. The method was evaluated against the latest state-of-the-art methods and achieved better performance by more than 20 %.