EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Aerial small target detection algorithm based on cross-scale separated attention

Ju Liang iD, Fan Wang iD, Jia Chen, Hai-Yan Huang, Zu-Fan Dou

PLOS One · 2025

DOI: 10.1371/journal.pone.0337318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Ju Liang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Application, Guilin University of Technology, Guilin, Guangxi, China. Hauptthemen laut MEDLINE: Algorithms, Unmanned Aerial Devices, Photography, Image Processing, Computer-Assisted. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Innovation Fund Project for College Teachers of Gansu Provincial Department of Education, Lanzhou Jiaotong University - Counterpart Support Universities Joint Innovation Fund Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In UAV aerial photography scenarios, targets exhibit characteristics such as multi-scale distribution, a high proportion of small targets, complex occlusions, and strong background interference. These characteristics impose high demands on detection algorithms in terms of fine-grained feature extraction, cross-scale fusion capability, and occlusion resistance.The YOLOv11s model has significant limitations in practical applications: its feature extraction module has a single semantic representation, the traditional feature pyramid network has limited capability to detect multi-scale targets, and it lacks an effective feature compensation mechanism when targets are occluded.To address these issues, we propose a UAV aerial small target detection algorithm named UAS-YOLO (Universal Inverted Bottleneck with Adaptive BiFPN and Separated and Enhancement Attention module YOLO), which incorporates three key optimizations. First, an Adaptive Bidirectional Feature Pyramid Network (ABiFPN) is designed as the Neck structure. Through cross-scale connections and dynamic weighted fusion, ABiFPN adjusts weight allocation based on target scale characteristics, focusing on enhancing feature integration for scales related to small targets and improving multi-scale feature representation capability. Second, a Separated and Enhancement Attention Module (SEAM) is introduced to replace the original SPPF module. This module focuses on key target regions, enhances effective feature responses in unoccluded areas, and specifically compensates for information loss in occluded regions, thereby improving the detection stability of occluded small targets. Third, a Universal Inverted Bottleneck (UIB) structure is proposed, which is fused with the C3K2 module to form the C3K2_UIB module. By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. Moreover, it demonstrates greater advantages compared to existing advanced algorithms, effectively addressing the challenge of small target detection in complex UAV scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsUnmanned Aerial DevicesPhotographyImage Processing, Computer-AssistedDetection Algorithms

Autor:innen und Institutionen

  • College of Computer Application, Guilin University of Technology, Guilin, Guangxi, China.
  • College of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu, China.
  • College of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou, Gansu, China.

ORCID-Profile: Ju Liang, Fan Wang

Förderung

  • National Natural Science Foundation of China
  • Innovation Fund Project for College Teachers of Gansu Provincial Department of Education
  • Lanzhou Jiaotong University - Counterpart Support Universities Joint Innovation Fund Project
  • Youth Science Fund of Lanzhou Jiaotong University
  • Computer Basic Education Teaching Research Project of the National Higher Education Institution Computer Basic Education Research Association

Zitieren

APA

Liang, J., Wang, F., Chen, J., Huang, H. Y., & Dou, Z. F. (2025). Aerial small target detection algorithm based on cross-scale separated attention. PLOS One. https://doi.org/10.1371/journal.pone.0337318

Vancouver

Liang J, Wang F, Chen J, Huang HY, Dou ZF. Aerial small target detection algorithm based on cross-scale separated attention. PLOS One. 2025. doi:10.1371/journal.pone.0337318

BibTeX
@article{Liang2025,
  author = {Liang, Ju and Wang, Fan and Chen, Jia and Huang, Hai-Yan and Dou, Zu-Fan},
  title = {Aerial small target detection algorithm based on cross-scale separated attention},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0337318}
}
Kostenlos starten →