Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 9, 2026ISPRS International Journal of Geo-InformationOpen Access

Controllable Spatio-Temporal Modeling of Pedestrian Spawn Dynamics for Urban Crowd Geosimulation

View Full Paper
Ask AI
Bookmark
Share

Authors

YLYan LyuBLBo LingWWWeiwei Wu

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates controllable spatio-temporal pedestrian dynamics in urban areas, suggesting enhanced crowd simulation accuracy.

Key Points

  • The research aims to create and assess a generative model for pedestrian spawn events, focusing on control over spatio-temporal dynamics.
  • Propose a Guided Joint Spatio-Temporal Diffusion framework for spawn simulation.
  • Integrate conditional denoising network with classifier-free guidance for user-specified factors.
  • Evaluate the model using next-event accuracy and fixed-horizon controllability on the Grand Central dataset.
  • Reduced temporal error (T-RMSE) by 38% when compared to strong baselines.
  • Achieved consistent improvements in spatial and spatio-temporal accuracy.
  • Demonstrated effective controllability in pedestrian-flow generation for geosimulation applications.

Cite This Study

Lyu et al. (2026) studied this question.

synapsesocial.com/papers/6a782d4e2e1896536c8403cchttps://doi.org/10.3390/ijgi15080356
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Data-driven physics-based modeling of pedestrian dynamics2024 · 2 citations
  2. 2HyPedSim: A Multi-Level Crowd-Simulation Framework—Methodology, Calibration, and Validation2024 · 6 citations
  3. 3Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion Model2026 · 2 citations
  4. 4A Data-driven Crowd Simulation Framework Integrating Physics-informed Machine Learning with Navigation Potential Fields2024
  5. 5Learning and Simulation of Spatiotemporally Multi-scale Pedestrian Flow Model2024 · 1 citations