Hydrodynamics-Informed Neural Network for Simulating Dense Crowd Motion Patterns

Yanshan Zhou, Pingrui Lai, Jiaqi Yu, Yingjie Xiong, Hua Yang

Abstract: With global occurrences of crowd crushes and stampedes, dense crowd simulation has been drawing great attention. In this research, our goal is to simulate dense crowd motions under six classic motion patterns, more specifically, to generate subsequent motions of dense crowds from the given initial states. Since dense crowds share similarities with fluids, such as continuity and fluidity, one common approach for dense crowd simulation is to construct hydrodynamics-based models, which consider dense crowds as fluids, guide crowd motions with Navier-Stokes equations, and conduct dense crowd simulation by solving governing equations. Despite the proposal of these models, dense crowd simulation faces multiple challenges, including the difficulty of directly solving Navier-Stokes equations due to their nonlinear nature, the ignorance of distinctive crowd characteristics which fluids lack, and the gaps in the evaluation and validation of crowd simulation models. To address the above challenges, we build a hydrodynamic model, which captures the crowd physical properties (continuity, fluidity, etc.) with Navier-Stokes equations and reflects the crowd social properties (sociality, personality, etc.) with operators that describe crowd interactions and crowd-environment interactions. To tackle the computational problem, we propose to solve the governing equation based on Navier-Stokes equations using neural networks, and introduce the Hydrodynamics-Informed Neural Network (HINN) which preserves the structure of the governing equation in its network architecture. To facilitate the evaluation, we construct a new dense crowd motion video dataset called Dense Crowd Flow Dataset (DCFD), containing six classic motion patterns (line, curve, circle, cross, cluster and scatter) and 457 video clips, which can serve as the groundtruths for various objective metrics. Numerous experiments are conducted using HINN to simulate dense crowd motions under six motion patterns with video clips from DCFD. Objective evaluation metrics that concerns authenticity, fidelity and diversity demonstrate the superior performance of our model in dense crowd simulation compared to other simulation models.

Primary Subject Area: [Content] Media Interpretation

Secondary Subject Area: [Generation] Generative Multimedia

Relevance To Conference: Crowd simulation has long been popular within computer vision due to its extensive applications. With global occurrences of crowd crushes and stampedes, how to understand and interpret dense crowd motions from multimedia has emerged as a prominent and timely topic of interest. In this work, we propose a hydrodynamic model that considers both crowd physical properties (continuity and fluidity) and social properties (sociality and personality), offering a comprehensive framework for simulating crowd motions in multimedia contexts. To tackle the computational challenges, we introduce the Hydrodynamics-Informed Neural Network (HINN) to solve our governing equation for dense crowd simulation, which aligns with current trends in multimedia research that leverage deep learning for simulation tasks. Additionally, we construct a new real-world dense crowd motion video dataset, which enables us to employ evaluation metrics concerning authenticity, fidelity and diversity for simulation models. These metrics are crucial for comprehensive multimedia content analysis and synthesis.

Submission Number: 3205