EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UAV-OBB: An aerial urban vehicle dataset with oriented bounding boxes for remote sensing object detection in smart cities

Israr Ahmad, Shang Fengjun, Kiran Bibi, Muhammad Salman Pathan

Data in Brief · 2026-06 · 66 · 112710

DOI: 10.1016/j.dib.2026.112710 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data in Brief, 2026-06. Verfasst von Israr Ahmad und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Urban smart city traffic management increasingly relies on UAV-based sensing, yet many widely used drone datasets annotate vehicles with axis-aligned bounding boxes that include unnecessary background and do not encode vehicle orientation. We present UAV-OBB, an aerial urban vehicle dataset with oriented bounding boxes (OBBs), designed for rotation-aware computer vision object detection and traffic monitoring from predominantly nadir-view UAV imagery. UAV-OBB contains 1617 RGB images at 1920 × 1080 resolution captured over roads in Chongqing and Wuhan (China), together with OBB Nannotations in YOLOv8-OBB label format and supplementary MP4 evaluation videos. The dataset provides 46,807 oriented annotations across six vehicle classes: bike, bus, car, other_vehicle, taxi, and truck, and is split into 1383 training images, 218 validation images, and 16 test images. Data were collected at 75 to 108 m altitude under diverse real-world conditions, including morning, midday, evening, night, rain, and mist or light fog, with both wide field-of-view and zoom settings to introduce strong scale variation. All instances were manually annotated using rotation-capable tools and double-checked for consistency, and occluded and truncated vehicles were included when the majority of the object was visible. To support practical smart city evaluation beyond static mAP, UAV-OBB also includes a short video clip with sparsely annotated reference frames and a longer unannotated sequence for qualitative assessment of temporal stability and deployment behaviour. UAV-OBB provides a realistic benchmark for rotation-aware detection, tracking, counting, and traffic flow analysis in urban UAV surveillance scenarios.

Schlagwörter

Stichwörter der Autor:innen

Aerial traffic surveillanceMulti-scale targetsNadir-view acquisitionOcclusion and truncationOverhead imageryRotated object annotationYOLOv8-OBB labels

Autor:innen und Institutionen

  • School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China.
  • Key Laboratory of Computer Network and Communication Technology, Chongqing, China.
  • Beijing Language and Culture University, Beijing, China.
  • ADAPT SFI Research Centre, School of Computing, Dublin City University, Ireland.

Zitieren

APA

Ahmad, I., Fengjun, S., Bibi, K., & Pathan, M. S. (2026). UAV-OBB: An aerial urban vehicle dataset with oriented bounding boxes for remote sensing object detection in smart cities. Data in Brief, 66, 112710. https://doi.org/10.1016/j.dib.2026.112710

Vancouver

Ahmad I, Fengjun S, Bibi K, Pathan MS. UAV-OBB: An aerial urban vehicle dataset with oriented bounding boxes for remote sensing object detection in smart cities. Data in Brief. 2026;66:112710. doi:10.1016/j.dib.2026.112710

BibTeX
@article{Ahmad2026,
  author = {Ahmad, Israr and Fengjun, Shang and Bibi, Kiran and Pathan, Muhammad Salman},
  title = {UAV-OBB: An aerial urban vehicle dataset with oriented bounding boxes for remote sensing object detection in smart cities},
  journal = {Data in Brief},
  year = {2026},
  volume = {66},
  pages = {112710},
  doi = {10.1016/j.dib.2026.112710}
}
Kostenlos starten →