eTraM: Event-based Traffic Monitoring Dataset
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911823222013952 |
|---|---|
| author | Verma, Aayush Atul Chakravarthi, Bharatesh Vaghela, Arpitsinh Wei, Hua Yang, Yezhou |
| author_facet | Verma, Aayush Atul Chakravarthi, Bharatesh Vaghela, Arpitsinh Wei, Hua Yang, Yezhou |
| contents | Event cameras, with their high temporal and dynamic range and minimal memory usage, have found applications in various fields. However, their potential in static traffic monitoring remains largely unexplored. To facilitate this exploration, we present eTraM - a first-of-its-kind, fully event-based traffic monitoring dataset. eTraM offers 10 hr of data from different traffic scenarios in various lighting and weather conditions, providing a comprehensive overview of real-world situations. Providing 2M bounding box annotations, it covers eight distinct classes of traffic participants, ranging from vehicles to pedestrians and micro-mobility. eTraM's utility has been assessed using state-of-the-art methods for traffic participant detection, including RVT, RED, and YOLOv8. We quantitatively evaluate the ability of event-based models to generalize on nighttime and unseen scenes. Our findings substantiate the compelling potential of leveraging event cameras for traffic monitoring, opening new avenues for research and application. eTraM is available at https://eventbasedvision.github.io/eTraM |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19976 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | eTraM: Event-based Traffic Monitoring Dataset Verma, Aayush Atul Chakravarthi, Bharatesh Vaghela, Arpitsinh Wei, Hua Yang, Yezhou Computer Vision and Pattern Recognition Event cameras, with their high temporal and dynamic range and minimal memory usage, have found applications in various fields. However, their potential in static traffic monitoring remains largely unexplored. To facilitate this exploration, we present eTraM - a first-of-its-kind, fully event-based traffic monitoring dataset. eTraM offers 10 hr of data from different traffic scenarios in various lighting and weather conditions, providing a comprehensive overview of real-world situations. Providing 2M bounding box annotations, it covers eight distinct classes of traffic participants, ranging from vehicles to pedestrians and micro-mobility. eTraM's utility has been assessed using state-of-the-art methods for traffic participant detection, including RVT, RED, and YOLOv8. We quantitatively evaluate the ability of event-based models to generalize on nighttime and unseen scenes. Our findings substantiate the compelling potential of leveraging event cameras for traffic monitoring, opening new avenues for research and application. eTraM is available at https://eventbasedvision.github.io/eTraM |
| title | eTraM: Event-based Traffic Monitoring Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.19976 |