YOLOv8-PSA: A YOLOv8 Enhanced by Partial Self-Attention Mechanism for Urban UAV Detection
Information Technology and Control · 25.09.2026 · 55 (3) · 1248-1265
DOI: 10.5755/j01.itc.55.3.45036 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Technology and Control, online erschienen am 25.09.2026. Verfasst von Yiwei Zhao und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Unmanned Aerial Vehicle (UAV) detection in urban environments is critical for airspace management and emergency response. However, dynamic scale variations, complex backgrounds, and real-time requirements hinder existing methods. This research proposes YOLOv8-PSA, which integrates a Partial Self-Attention (PSA) mechanism to capture global contextual dependencies and suppress background noise. A multi-scale feature fusion module with a lightweight C2fCIB block enhances detection accuracy across varying scales. CIoU loss is adopted to optimize bounding box localization. Experiments on an urban UAV dataset demonstrate 97.8% precision, 92.5% recall, and 96.5% mAP50, with consistent improvements over the baseline YOLOv8n. Comparative and ablation studies validate the effectiveness of the proposed modules for practical urban UAV detection.
Zitieren
APA
Zhao, Y., Chen, Y., & Liu, Y. (2026). YOLOv8-PSA: A YOLOv8 Enhanced by Partial Self-Attention Mechanism for Urban UAV Detection. Information Technology and Control, 55(3), 1248-1265. https://doi.org/10.5755/j01.itc.55.3.45036
Vancouver
Zhao Y, Chen Y, Liu Y. YOLOv8-PSA: A YOLOv8 Enhanced by Partial Self-Attention Mechanism for Urban UAV Detection. Information Technology and Control. 2026;55(3):1248-1265. doi:10.5755/j01.itc.55.3.45036
BibTeX
@article{Zhao2026,
author = {Zhao, Yiwei and Chen, Yu and Liu, Yiyao},
title = {YOLOv8-PSA: A YOLOv8 Enhanced by Partial Self-Attention Mechanism for Urban UAV Detection},
journal = {Information Technology and Control},
year = {2026},
volume = {55},
number = {3},
pages = {1248--1265},
doi = {10.5755/j01.itc.55.3.45036}
}
EUVIMED