Crowds by Example

TLDR

Crowd simulation methods typically rely on simple rule sets, which restrict the behavioral richness of simulated agents. This work introduces an example‑based crowd simulation technique. The method learns from tracked video of real pedestrians, creating example trajectories that agents retrieve during simulation to mimic natural behavior. Agents copy trajectories from similar real‑world situations, producing realistic, natural-looking movements.

Abstract

Abstract We present an example‐based crowd simulation technique. Most crowd simulation techniques assume that the behavior exhibited by each person in the crowd can be defined by a restricted set of rules. This assumption limits the behavioral complexity of the simulated agents. By learning from real‐world examples, our autonomous agents display complex natural behaviors that are often missing in crowd simulations. Examples are created from tracked video segments of real pedestrian crowds. During a simulation, autonomous agents search for examples that closely match the situation that they are facing. Trajectories taken by real people in similar situations, are copied to the simulated agents, resulting in seemingly natural behaviors.