基于YOLOv8n的无人机航拍目标检测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(62173171)


UAV Aerial Photography Target Detection Based on YOLOv8n
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 增强出版
  • |
  • 文章评论
    摘要:

    针对无人机航拍检测任务中小目标检测精度低的问题, 提出一种基于YOLOv8n的目标检测算法(SFE-YOLO). 首先, 嵌入浅层特征增强模块, 将输入特征的浅层空间信息与颈部获取的深层语义信息融合, 以增强小目标特征表示能力, 并使用全局上下文块(GC-Block)对融合信息进行重校准, 抑制背景噪声. 其次, 引入可变形卷积来代替C2F中的部分标准卷积, 提高网络对几何变化的适应性. 再次, 引入ASPPF模块, 融合平均池化技术, 增强模型对多尺度特征的表达并降低漏检率. 最后, 在颈部网络的基础上嵌入中尺度特征合成层, 融合主干网络中更多的中间特征, 使不同尺度的特征过渡更平滑, 并通过跳跃连接增强特征重用性. 该模型在数据集VisDrone2019和VOC2012上进行验证, mAP@0.5值达到30.5%和67.3%, 相较于基线算法YOLOv8n提升了3.6%和0.8%, 能够提升无人机图像目标检测性能, 同时具有较好的泛化性.

    Abstract:

    An enhanced YOLOv8n-based object detection algorithm, SFE-YOLO, is developed to tackle the issues of low detection precision for small targets in UAV aerial photography. Initially, a shallow feature enhancement module is embedded to integrate the shallow spatial details of input features with deep semantic information obtained from the neck section. This fusion strengthens the representation capability for small target features. Additionally, a global context block (GC-Block) is utilized to recalibrate this merged information, effectively suppressing background noise. Subsequently, the network’s adaptability to geometric changes is increased by substituting deformable convolutions for some standard convolutions in the C2F layer. Furthermore, the ASPPF module, incorporating average pooling technology, is integrated to augment the model’s expression of multi-scale features and to decrease miss rates. Finally, a novel weighted feature fusion method is designed. This method blends more intermediate features from the main network, enabling smoother transitions among different scale features and augmenting feature reusability through skip connections. The model’s performance is validated on VisDrone2019 and VOC2012 datasets, achieving mAP@0.5 values of 30.5% and 67.3%, respectively. These results mark improvements of 3.6% and 0.8% over the baseline YOLOv8n algorithm, demonstrating enhanced performance in UAV image target detection and notable generalization capabilities.

    参考文献
    相似文献
    引证文献
引用本文

沈学利,王灵超.基于YOLOv8n的无人机航拍目标检测.计算机系统应用,,():1-10

复制
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:2024-01-17
  • 最后修改日期:2024-02-26
  • 录用日期:
  • 在线发布日期: 2024-06-05
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号