TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Mengyu, Zhou, Xingcheng, Chen, Guang, Knoll, Alois, Cao, Hu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911328822624256
author Li, Mengyu
Zhou, Xingcheng
Chen, Guang
Knoll, Alois
Cao, Hu
author_facet Li, Mengyu
Zhou, Xingcheng
Chen, Guang
Knoll, Alois
Cao, Hu
contents In Intelligent Transportation Systems (ITS), multi-object tracking is primarily based on frame-based cameras. However, these cameras tend to perform poorly under dim lighting and high-speed motion conditions. Event cameras, characterized by low latency, high dynamic range and high temporal resolution, have considerable potential to mitigate these issues. Compared to frame-based vision, there are far fewer studies on event-based vision. To address this research gap, we introduce an initial pilot dataset tailored for event-based ITS, covering vehicle and pedestrian detection and tracking. We establish a tracking-by-detection benchmark with a specialized feature extractor based on this dataset, achieving excellent performance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14595
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios
Li, Mengyu
Zhou, Xingcheng
Chen, Guang
Knoll, Alois
Cao, Hu
Computer Vision and Pattern Recognition
In Intelligent Transportation Systems (ITS), multi-object tracking is primarily based on frame-based cameras. However, these cameras tend to perform poorly under dim lighting and high-speed motion conditions. Event cameras, characterized by low latency, high dynamic range and high temporal resolution, have considerable potential to mitigate these issues. Compared to frame-based vision, there are far fewer studies on event-based vision. To address this research gap, we introduce an initial pilot dataset tailored for event-based ITS, covering vehicle and pedestrian detection and tracking. We establish a tracking-by-detection benchmark with a specialized feature extractor based on this dataset, achieving excellent performance.
title TUMTraf EMOT: Event-Based Multi-Object Tracking Dataset and Baseline for Traffic Scenarios
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.14595