Interactive Crowd Content Generation and Analysis using Trajectory-level Behavior Learning
Sujeong Kim, Aniket Bera, Andrew Best, Rohan Chabra, and Dinesh Manocha
University of North Carolina at Chapel-Hill
We present an adaptive data-driven algorithm for interactive crowd simulation. Our approach combines realistic trajectory behaviors extracted from videos with synthetic multi-agent algorithms to generate plausible simulations. We use statistical techniques to compute the movement patterns and motion dynamics from noisy 2D trajectories extracted from crowd videos. These learned pedestrian dynamic characteristics are used to generate collision-free trajectories of virtual pedestrians in slightly different environments or situations. The overall approach is robust and can generate perceptually realistic crowd movements at interactive rates in dynamic environments. We also present results from preliminary user studies that evaluate the trajectory behaviors generated by our algorithm. |
[Video]
[Video - Real-time rendering using Unreal Engine]
[Figures]


[Downloads]
[pdf][Related Work]
-
GLMP- Realtime Pedestrian Path Prediction using Global and Local Movement Patterns [Project Page]
-
Interactive Crowd Content Generation and Analysis using Trajectory-level Behavior Learning, ISM 2015 [Project Page]
-
BRVO: Predicting Pedestrian Trajectories using Velocity-Space Reasoning, IJRR 2015 [Project Page]
-
Efficient Trajectory Extraction and Parameter Learning for Data-Driven Crowd Simulation, Graphics Interface 2015 [Project Page]