SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chanda, Kaustav, Verma, Aayush Atul, Vaghela, Arpitsinh, Yang, Yezhou, Chakravarthi, Bharatesh
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915392099713024
author Chanda, Kaustav
Verma, Aayush Atul
Vaghela, Arpitsinh
Yang, Yezhou
Chakravarthi, Bharatesh
author_facet Chanda, Kaustav
Verma, Aayush Atul
Vaghela, Arpitsinh
Yang, Yezhou
Chakravarthi, Bharatesh
contents Event-based sensors have emerged as a promising solution for addressing challenging conditions in pedestrian and traffic monitoring systems. Their low-latency and high dynamic range allow for improved response time in safety-critical situations caused by distracted walking or other unusual movements. However, the availability of data covering such scenarios remains limited. To address this gap, we present SEPose -- a comprehensive synthetic event-based human pose estimation dataset for fixed pedestrian perception generated using dynamic vision sensors in the CARLA simulator. With nearly 350K annotated pedestrians with body pose keypoints from the perspective of fixed traffic cameras, SEPose is a comprehensive synthetic multi-person pose estimation dataset that spans busy and light crowds and traffic across diverse lighting and weather conditions in 4-way intersections in urban, suburban, and rural environments. We train existing state-of-the-art models such as RVT and YOLOv8 on our dataset and evaluate them on real event-based data to demonstrate the sim-to-real generalization capabilities of the proposed dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11910
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
Chanda, Kaustav
Verma, Aayush Atul
Vaghela, Arpitsinh
Yang, Yezhou
Chakravarthi, Bharatesh
Computer Vision and Pattern Recognition
Event-based sensors have emerged as a promising solution for addressing challenging conditions in pedestrian and traffic monitoring systems. Their low-latency and high dynamic range allow for improved response time in safety-critical situations caused by distracted walking or other unusual movements. However, the availability of data covering such scenarios remains limited. To address this gap, we present SEPose -- a comprehensive synthetic event-based human pose estimation dataset for fixed pedestrian perception generated using dynamic vision sensors in the CARLA simulator. With nearly 350K annotated pedestrians with body pose keypoints from the perspective of fixed traffic cameras, SEPose is a comprehensive synthetic multi-person pose estimation dataset that spans busy and light crowds and traffic across diverse lighting and weather conditions in 4-way intersections in urban, suburban, and rural environments. We train existing state-of-the-art models such as RVT and YOLOv8 on our dataset and evaluate them on real event-based data to demonstrate the sim-to-real generalization capabilities of the proposed dataset.
title SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.11910