Detecting anomalies in dense 3D crowds
Fecha
2025-08
Título de la revista
ISSN de la revista
Título del volumen
Editor
Elsevier
Resumen
Estimating the behavior of dense 3D crowds is crucial for applications in security, surveillance, and planning. Detecting events in such crowds from a single video, the most common scenario, is challenging due to ambiguities, occlusions, and complex human behavior. To address this, we propose a method that overlays pixel-based labels on video data to highlight anomalies in dense 3D crowds movement. Our key contribution is a data-driven, image-based model trained on features derived from 3D virtual crowd animations of articulated characters that mimic real crowds at a micro-level. By using training data based on captured dense crowd trajectories and realistic 3D motions, we can analyze and detect anomalies in complex real-world scenarios. Additionally, while acquiring ground-truth data from diverse viewpoints is difficult in real-world settings, our virtual simulator allows rendering scenes from multiple perspectives, enabling the training of models robust to viewpoint variations. We demonstrate qualitatively and quantitatively that our method can detect anomalies in much denser crowds than existing methods.
Descripción
This work has been partially funded by: the Spanish State Agency of Research under grant agreement TED2021-132003B-I00; by the Universidad Rey Juan Carlos through the Distinguished Researcher position INVESDIST-04 under the call from 17/12/2020; by Spanish Ministry of Science and Innovation under grant agreement CNS2022-13599; and by European Union’s Horizon 2020 research and innovation program under grant agreement No 899739 (H2020-FETOPEN-2018-2020 CrowdDNA project).
Palabras clave
Citación
Melania Prieto-Martín, Marc Comino-Trinidad, Dan Casas, Detecting anomalies in dense 3D crowds, Computers & Graphics, Volume 130, 2025, 104267, ISSN 0097-8493, https://doi.org/10.1016/j.cag.2025.104267
Colecciones

Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution-NonCommercial-NoDerivatives 4.0 International