Guardado en:
Detalles Bibliográficos
Autores principales: Wijaya, Antonius Bima Murti, Henderson, Paul, Mahmoud, Marwa
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.18166
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914408522842112
author Wijaya, Antonius Bima Murti
Henderson, Paul
Mahmoud, Marwa
author_facet Wijaya, Antonius Bima Murti
Henderson, Paul
Mahmoud, Marwa
contents Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works address the problem by predicting individual trajectories and considering surrounding objects based on manually annotated data. However, these approaches tend to overlook dense crowd scenarios, where the challenges of automation become more pronounced due to the massiveness, noisiness, and inaccuracy of the tracking outputs, resulting in high computational costs. To address these challenges, we propose and extensively evaluate a novel cluster-based approach that groups individuals based on similar attributes over time, enabling faster execution through accurate group summarisation. Our plug-and-play method can be combined with existing trajectory predictors by using our output centroid in place of their pedestrian input. We evaluate our proposed method on several challenging dense crowd scenes. We demonstrated that our approach leads to faster processing and lower memory usage when compared with state-of-the-art methods, while maintaining the accuracy
format Preprint
id arxiv_https___arxiv_org_abs_2603_18166
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
Wijaya, Antonius Bima Murti
Henderson, Paul
Mahmoud, Marwa
Artificial Intelligence
Crowd trajectory prediction plays a crucial role in public safety and management, where it can help prevent disasters such as stampedes. Recent works address the problem by predicting individual trajectories and considering surrounding objects based on manually annotated data. However, these approaches tend to overlook dense crowd scenarios, where the challenges of automation become more pronounced due to the massiveness, noisiness, and inaccuracy of the tracking outputs, resulting in high computational costs. To address these challenges, we propose and extensively evaluate a novel cluster-based approach that groups individuals based on similar attributes over time, enabling faster execution through accurate group summarisation. Our plug-and-play method can be combined with existing trajectory predictors by using our output centroid in place of their pedestrian input. We evaluate our proposed method on several challenging dense crowd scenes. We demonstrated that our approach leads to faster processing and lower memory usage when compared with state-of-the-art methods, while maintaining the accuracy
title Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
topic Artificial Intelligence
url https://arxiv.org/abs/2603.18166