Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environments
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913560786894848 |
|---|---|
| author | Honarvar, Sara Diaz-Mercado, Yancy |
| author_facet | Honarvar, Sara Diaz-Mercado, Yancy |
| contents | Modeling human trajectories in crowded environments is challenging due to the complex nature of pedestrian behavior and interactions. This paper proposes a geometric graph neural network (GNN) architecture that integrates domain knowledge from psychological studies to model pedestrian interactions and predict future trajectories. Unlike prior studies using complete graphs, we define interaction neighborhoods using pedestrians' field of view, motion direction, and distance-based kernel functions to construct graph representations of crowds. Evaluations across multiple datasets demonstrate improved prediction accuracy through reduced average and final displacement error metrics. Our findings underscore the importance of integrating domain knowledge with data-driven approaches for effective modeling of human interactions in crowds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17409 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environments Honarvar, Sara Diaz-Mercado, Yancy Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics Systems and Control Modeling human trajectories in crowded environments is challenging due to the complex nature of pedestrian behavior and interactions. This paper proposes a geometric graph neural network (GNN) architecture that integrates domain knowledge from psychological studies to model pedestrian interactions and predict future trajectories. Unlike prior studies using complete graphs, we define interaction neighborhoods using pedestrians' field of view, motion direction, and distance-based kernel functions to construct graph representations of crowds. Evaluations across multiple datasets demonstrate improved prediction accuracy through reduced average and final displacement error metrics. Our findings underscore the importance of integrating domain knowledge with data-driven approaches for effective modeling of human interactions in crowds. |
| title | Geometric Graph Neural Network Modeling of Human Interactions in Crowded Environments |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics Systems and Control |
| url | https://arxiv.org/abs/2410.17409 |