轻量化YOLOv7-tiny的遥感图像小目标检测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

A

基金项目:

国家自然科学基金项目(No. 61602226)、辽宁省教育厅科学研究基金项目(No. LJKQZ2021152; No. LJ2020JCL007)、校引进人才基金项目(No. 18-1021)


Lightweight YOLOv7-tiny for remote sensing image small target detection
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:

    针对遥感图像小目标众多、目标检测器参数量大和检测效率低等问题,提出一种改进的YOLOv7-tiny的轻量级遥感图像小目标检测模型。首先,针对原始模型中跨阶段局部空间金字塔池化网络复杂的碎片化操作,提出轻量级的空间金字塔池化结构来减少多余的卷积算子操作;其次,针对颈部网络冗余的模块化连接方式和小目标容易在深层特征丢失空间信息的问题,提出深层语义信息引导的单尺度预测头方法来进行小目标位置信息强化,并进一步减少颈部网络和头部网络的计算成本。在遥感图像数据集上展开实验,结果表明,改进后的模型比原始模型参数量降低49.6%,计算复杂度降低28.5%,推理速度提高73.1%,并优于现阶段其他主流轻量级目标检测器。。

    Abstract:

    Aiming at the problems of numerous small targets in remote sensing images, large number of target detector pa-rameters and low detection efficiency, an improved lightweight remote sensing image small target detection model of YOLOv7-tiny is proposed. First, to address the complex fragmentation operations of the cross-stage local spatial pyramidal pooling network in the original model, a lightweight spatial pyramidal pooling structure is proposed to reduce the redundant convolution operator operations; second, to address the problems of redundant modular con-nectivity of the neck network and the easy loss of spatial information of small targets in deep features, a single-scale prediction head method guided by deep semantic information is proposed to reduce the neck network and head network to reduce the computational cost of the neck network and head network. Experiments are carried out on remote sensing image datasets, and the results show that the improved model reduces the number of parameters by 49.6%, computational complexity by 28.5%, and inference speed by 73.1% compared with the original model, and outperforms other mainstream lightweight target detectors at this stage.

    参考文献
    相似文献
    引证文献
引用本文

桑雨,李立权,李铁. 轻量化YOLOv7-tiny的遥感图像小目标检测[J]. 科学技术与工程, 2024, 24(18): 7726-7732.
Sang Yu, Li liqun, Li Tie. Lightweight YOLOv7-tiny for remote sensing image small target detection[J]. Science Technology and Engineering,2024,24(18):7726-7732.

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:2023-06-16
  • 最后修改日期:2024-04-18
  • 录用日期:2023-10-26
  • 在线发布日期: 2024-07-05
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注
《科学技术与工程》入选维普《中文科技期刊数据库》自然科学类期刊月度下载排行榜TOP10