Scholarlink

<p>To address the challenges associated with dense and occluded targets in small target detection utilizing unmanned aerial vehicle (UAV), we propose an enhanced detection algorithm referred as the YOLOv8n-ACW. Building upon the YOLOv8n baseline network model, we have integrated Adown into the Backbone and developed a CCDHead to further improve the drone’s capability to recognize small targets. Additionally, WIoU-V3 has been introduced as the loss function. Experiment results derived from the Visdrone2019 dataset indicate that, the YOLOv8n- ACW has achieved a 4.2% increase in mAP50(%) compared to the baseline model, while simultaneously reducing the parameter count by 36.7%, exhibiting superior capabilities in detecting small targets. Furthermore, utilizing a self-constructed dataset of G5-Pro drones for target detection experiments, the results indicate that the enhanced model has robust generalization capabilities in real-world environments. The UAV target detection experiment combines experimental simulation with real-world testing, while combining scientific exploration with educational objectives. This experiment has high fidelity, excellent functional scalability, and strong practicality, aiming to cultivate students’ comprehensive practical and innovative abilities.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Experiment study on UAV target detection algorithm based on YOLOv8n-ACW

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月2日

查看全文
  • Bo Xue,
  • Bowen Zhang,
  • Qin Cheng

摘要

To address the challenges associated with dense and occluded targets in small target detection utilizing unmanned aerial vehicle (UAV), we propose an enhanced detection algorithm referred as the YOLOv8n-ACW. Building upon the YOLOv8n baseline network model, we have integrated Adown into the Backbone and developed a CCDHead to further improve the drone’s capability to recognize small targets. Additionally, WIoU-V3 has been introduced as the loss function. Experiment results derived from the Visdrone2019 dataset indicate that, the YOLOv8n- ACW has achieved a 4.2% increase in mAP50(%) compared to the baseline model, while simultaneously reducing the parameter count by 36.7%, exhibiting superior capabilities in detecting small targets. Furthermore, utilizing a self-constructed dataset of G5-Pro drones for target detection experiments, the results indicate that the enhanced model has robust generalization capabilities in real-world environments. The UAV target detection experiment combines experimental simulation with real-world testing, while combining scientific exploration with educational objectives. This experiment has high fidelity, excellent functional scalability, and strong practicality, aiming to cultivate students’ comprehensive practical and innovative abilities.