Scholarlink

<p>In this study, Cross-YOLO, an enhanced version of the YOLOv8 model, is specifically designed to address the challenge of detecting small objects in UAV target detection scenarios. The model refines the original YOLOv8 through several innovative improvements: Firstly, in order to improve the detection accuracy of small targets, we propose Cross-FPN to bolster the original FPN. Secondly, we have redesigned a lightweight detection head, DELDH, to solve the problem of network bloat caused by the introduction of small object detection heads. Thirdly, a new attention mechanism CMCA is designed, that unifies the Coordinate attention mechanism with the Multi-scale convolutional attention mechanism to further enhance the feature extraction of small targets. Finally, the WIoU loss function is introduced to improve the accuracy of bounding box regression and improve detection performance. Experimental data in the Visdrone dataset indicate that, under the condition of the selected model size n, Cross-YOLO achieves a substantial reduction of 35.4% in parameter count compared to YOLOv8n, with only a marginal increase of 7.8% in computational load, and a significant improvement of 5.3% in <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11760_2025_4084_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="55" /> </InlineMediaObject> <EquationSource Format="TEX">\(mAP_{0.5}\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>m</mi> <mi>A</mi> <msub> <mi>P</mi> <mrow> <mn>0.5</mn> </mrow> </msub> </mrow> </math></EquationSource> </InlineEquation>. Furthermore, its strong performance on the DOTA v1.5 and TinyPerson datasets confirms the model’s generalization capabilities and practical applicability.</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

Cross-YOLO: an object detection algorithm for UAV based on improved YOLOv8 model

  • 期刊论文

  • 发表日期：

    2025年4月16日

查看全文
  • Ying Dong,
  • Jiahao Guo,
  • Fucheng Xu

摘要

In this study, Cross-YOLO, an enhanced version of the YOLOv8 model, is specifically designed to address the challenge of detecting small objects in UAV target detection scenarios. The model refines the original YOLOv8 through several innovative improvements: Firstly, in order to improve the detection accuracy of small targets, we propose Cross-FPN to bolster the original FPN. Secondly, we have redesigned a lightweight detection head, DELDH, to solve the problem of network bloat caused by the introduction of small object detection heads. Thirdly, a new attention mechanism CMCA is designed, that unifies the Coordinate attention mechanism with the Multi-scale convolutional attention mechanism to further enhance the feature extraction of small targets. Finally, the WIoU loss function is introduced to improve the accuracy of bounding box regression and improve detection performance. Experimental data in the Visdrone dataset indicate that, under the condition of the selected model size n, Cross-YOLO achieves a substantial reduction of 35.4% in parameter count compared to YOLOv8n, with only a marginal increase of 7.8% in computational load, and a significant improvement of 5.3% in \(mAP_{0.5}\) m A P 0.5 . Furthermore, its strong performance on the DOTA v1.5 and TinyPerson datasets confirms the model’s generalization capabilities and practical applicability.