EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SF‐YOLO: A Novel YOLO Framework for Small Object Detection in Aerial Scenes

Meng Sun, Le Wang, Wangyu Jiang, Fayaz Ali Dharejo, Guojun Mao, Radu Timofte

IET Image Processing · 2025-01 · 19 (1)

DOI: 10.1049/ipr2.70027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 03.03.2025. Verfasst von Meng Sun und 5 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Alexander von Humboldt-Stiftung, Natural Science Foundation of Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection models are widely applied in the fields such as video surveillance and unmanned aerial vehicles to enable the identification and monitoring of various objects on a diversity of backgrounds. The general CNN‐based object detectors primarily rely on downsampling and pooling operations, often struggling with small objects that have low resolution and failing to fully leverage contextual information that can differentiate objects from complex background. To address the problems, we propose a novel YOLO framework called SF‐YOLO for small object detection. Firstly, we present a spatial information perception (SIP) module to extract contextual features for different objects through the integration of space to depth operation and large selective kernel module, which dynamically adjusts receptive field of the backbone and obtains the enhanced features for richer understanding of differentiation between objects and background. Furthermore, we design a novel multi‐scale feature weighted fusion strategy, which performs weighted fusion on feature maps by combining fast normalized fusion method and CARAFE operation, accurately assessing the importance of each feature and enhancing the representation of small objects. The extensive experiments conducted on VisDrone2019, Tiny‐Person and PESMOD datasets demonstrate that our proposed method enables comparable detection performance to state‐of‐the‐art detectors.

Förderung

  • Alexander von Humboldt-Stiftung
  • Natural Science Foundation of Fujian Province

Zitieren

APA

Sun, M., Wang, L., Jiang, W., Dharejo, F. A., Mao, G., & Timofte, R. (2025). SF‐YOLO: A Novel YOLO Framework for Small Object Detection in Aerial Scenes. IET Image Processing, 19(1). https://doi.org/10.1049/ipr2.70027

Vancouver

Sun M, Wang L, Jiang W, Dharejo FA, Mao G, Timofte R. SF‐YOLO: A Novel YOLO Framework for Small Object Detection in Aerial Scenes. IET Image Processing. 2025;19(1). doi:10.1049/ipr2.70027

BibTeX
@article{Sun2025,
  author = {Sun, Meng and Wang, Le and Jiang, Wangyu and Dharejo, Fayaz Ali and Mao, Guojun and Timofte, Radu},
  title = {SF‐YOLO: A Novel YOLO Framework for Small Object Detection in Aerial Scenes},
  journal = {IET Image Processing},
  year = {2025},
  volume = {19},
  number = {1},
  doi = {10.1049/ipr2.70027}
}
Kostenlos starten →