A statistical similarity measure for aggregate crowd dynamics

Stephen J. Guy, Jur Van Den Berg, Wenxi Liu, Rynson Lau, Ming C. Lin, Dinesh Manocha

Research output: Contribution to journalArticlepeer-review

107 Scopus citations


We present an information-theoretic method to measure the similarity between a given set of observed, real-world data and visual simulation technique for aggregate crowd motions of a complex system consisting of many individual agents. This metric uses a two-step process to quantify a simulator's ability to reproduce the collective behaviors of the whole system, as observed in the recorded realworld data. First, Bayesian inference is used to estimate the simulation states which best correspond to the observed data, then a maximum likelihood estimator is used to approximate the prediction errors. This process is iterated using the EM-algorithm to produce a robust, statistical estimate of the magnitude of the prediction error as measured by its entropy (smaller is better). This metric serves as a simulator-to-data similarity measurement. We evaluated the metric in terms of robustness to sensor noise, consistency across different datasets and simulation methods, and correlation to perceptual metrics.

Original languageEnglish (US)
Article number190
JournalACM Transactions on Graphics
Issue number6
StatePublished - Nov 2012


  • Crowd simulation
  • Data-driven simulations
  • Validation


Dive into the research topics of 'A statistical similarity measure for aggregate crowd dynamics'. Together they form a unique fingerprint.

Cite this