EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism

Zhe Quan, Jun Sun iD

Sensors · 20.01.2025 · 25 (2) · 589

DOI: 10.3390/s25020589 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.01.2025. Verfasst von Zhe Quan und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of AI algorithms and computational power, object recognition based on deep learning frameworks has become a major research direction in computer vision. UAVs equipped with object detection systems are increasingly used in fields like smart transportation, disaster warning, and emergency rescue. However, due to factors such as the environment, lighting, altitude, and angle, UAV images face challenges like small object sizes, high object density, and significant background interference, making object detection tasks difficult. To address these issues, we use YOLOv8s as the basic framework and introduce a multi-level feature fusion algorithm. Additionally, we design an attention mechanism that links distant pixels to improve small object feature extraction. To address missed detections and inaccurate localization, we replace the detection head with a dynamic head, allowing the model to route objects to the appropriate head for final output. We also introduce Slideloss to improve the model’s learning of difficult samples and ShapeIoU to better account for the shape and scale of bounding boxes. Experiments on datasets like VisDrone2019 show that our method improves accuracy by nearly 10% and recall by about 11% compared to the baseline. Additionally, on the AI-TODv1.5 dataset, our method improves the mAP50 from 38.8 to 45.2.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismdetection headfeature pyramid networkloss functionsmall object detection

Autor:innen und Institutionen

  • School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China.

ORCID-Profile: Jun Sun

Zitieren

APA

Quan, Z., & Sun, J. (2025). A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism. Sensors, 25(2), 589. https://doi.org/10.3390/s25020589

Vancouver

Quan Z, Sun J. A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism. Sensors. 2025;25(2):589. doi:10.3390/s25020589

BibTeX
@article{Quan2025,
  author = {Quan, Zhe and Sun, Jun},
  title = {A Feature-Enhanced Small Object Detection Algorithm Based on Attention Mechanism},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {2},
  pages = {589},
  doi = {10.3390/s25020589}
}
Kostenlos starten →