改进YOLOv8的无人机航拍图像小目标检测算法

DOI:
CSTR:
作者:
作者单位:

1.青岛科技大学自动化与电子工程学院;2.青岛科技大学机电工程学院

作者简介:

通讯作者:

中图分类号:

TP391.41 TN919.5

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Improve the Small Target Detection Algorithm of YOLOv8 UAV Aerial Image
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对无人机航拍图像中存在的小目标特征提取能力不足及尺度多样性的问题,提出了一种改进YOLOv8的无人机航拍图像目标检测算法。首先,新增小目标检测层P2,增强模型的小目标检测能力。其次,设计了双向特征对齐融合方法对颈部进行改进,结合特征对齐模块和双向特征金字塔的思想,提升模型的多尺度融合能力,实现更完整的特征融合。然后,设计了双层路由-空间注意力模块加入主干中,通过串联双层路由注意力和空间注意力模块,加强对目标的特征捕获能力。最后,设计了损失函数Focaler-XIoU,解决样本难易分布对边框回归的影响,增强模型的稳定性和检测效果。实验结果表明,改进的网络模型在VisDrone数据集上mAP50提升了9.2%,相比目前主流的目标检测算法,有更优的检测效果,能够很好地完成无人机航拍图像检测任务。

    Abstract:

    Aiming at the problems of low feature extraction capability and scale diversity in UAV aerial images, an improved YOLOv8 object detection algorithm for UAV aerial images is proposed. Firstly, P2 layer is added to enhance the small target detection capability of the model. Secondly, the bidirectional feature alignment fusion method is designed to improve the neck. Combining the idea of feature alignment module and bidirectional feature pyramid, the multi-scale fusion capability of the model is improved to achieve a more complete feature fusion. Then, bi-level routing-spatial attention module is designed and added to the backbone. By connecting the bi-level routing attention module and spatial attention module, the feature capturing ability of the target is strengthened. Finally, the loss function Focaler-XIoU is designed to solve the influence of sample difficulty distribution on border regression, and enhance the stability and detection effect of the model. The experimental results show that the improved network model has improved the VisDrone dataset mAP50 by 9.2%, which has better detection effect than the current mainstream target detection algorithm, and can well complete the UAV aerial image detection task.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-04-22
  • 最后修改日期:2024-07-11
  • 录用日期:2024-07-11
  • 在线发布日期:
  • 出版日期:
文章二维码
×
《电子测量技术》
财务封账不开票通知