Model-based Crowd Behaviors in Human-solution Space
Computer Graphics Forum, 2023, 42(6): e14919.
Wei Xiang, He Wang, Yuqing Zhang, Milo K. Yip and Xiaogang Jin
Overview of our simulation framework. Taking the real data as input (a), our method employs a physics-inspired energy model which describes path planning with a multi-granularity control (b), and solves the minimizer in human-solution space by leveraging an acceleration-aware data-driven scheme. As a result, we can generate different crowd behaviors in diverse scenes (c).
Abstract
Realistic crowd
simulation has been pursued for decades, but it still necessitates tedious
human labor and a lot of trial and error. The majority of currently used
crowd modeling is either empirical (model-based) or data-driven
(model-free). Model based methods cannot fit observed data precisely,
whereas model-free methods are limited by the availability/quality of data
and are uninterpretable. In this paper, we aim at taking advantage of both
model-based and data-driven approaches. In order to accomplish this, we
propose a new simulation framework built on a physics-based model that is
designed to be data-friendly. Both the general prior knowledge about crowds
encoded by the physics-based model and the specific real-world crowd data at
hand jointly influence the system dynamics. With a multi-granularity
physics-based model, the framework combines microscopic and macroscopic
motion control. Each simulation step is formulated as an energy optimization
problem, where the minimizer is the desired crowd behavior. In contrast to
traditional optimization-based methods which seek the theoretical minimizer,
we designed an acceleration-aware data-driven scheme to compute the
minimizer from real-world data in order to achieve higher realism by
parameterizing both velocity and acceleration. Experiments demonstrate that
our method can produce crowd animations that are more realistically behaved
in a variety of scales and scenarios when compared to the earlier methods.