Context-Aware Anomaly Detection of Pedestrian Trajectories in Urban Back Streets Using a Variational Autoencoder

Detecting anomalous pedestrian behaviors is critical for enhancing safety in dense urban environments, particularly in complex back streets where movement patterns are irregular and context-dependent. While extensive research has been conducted on trajectory-based anomaly detection for vehicles, shi...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Juyeon Cho, Youngok Kang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2025-11-01
coleção:	ISPRS International Journal of Geo-Information
Assuntos:	pedestrian trajectory anomaly detection spatiotemporal analysis alleyway Variational Autoencoder (VAE)
Acesso em linha:	https://www.mdpi.com/2220-9964/14/11/438
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!