基于改进的YOLOv5s小目标船舶遥感图像检测
DOI:
作者:
作者单位:

长江大学计算机科学学院

作者简介:

通讯作者:

中图分类号:

TP391.4;TP751

基金项目:

国家自然科学基金(编号:61771354);


Small target ship remote sensing image detection based on improved YOLOv5s
Author:
Affiliation:

School of Computer Science,Yangtze University

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:

    遥感图像中船舶目标具有多尺度特性,背景多变及气象复杂等特点,导致小目标船舶检测存在精度低,出现误检,漏检等情况。针对上述情况,提出了一种基于YOLOv5s的小目标船舶检测改进模型。首先,为解决船舶检测中尺度变化和背景多变问题,引入了适应空间特征融合(ASFF)模块,其次,为减少检测网络的计算量和参数量引入了BoTNet注意力机制,然后为提升网络整体的检测精确度,使用了EIoU边框损失函数,最后为保证网络整体的轻量化引入了Slim-neck颈部网络。实验显示,在主要数据集LEVIR-Ship上,相较于基准YOLOv5s,mAp@0.5提升了7.1%达到了81.3%,参数量降低了0.44M,计算量降低了0.6GFLOPs,权重降低了0.9M。提出的方法在各项关键指标中表现更为优秀,实现了复杂环境下高精度的小目标船舶检测。在验证数据集McShips上进行对比实验。实验表明,所提出方法依然表现更为优秀,验证了所提方法具有普适性。

    Abstract:

    Ship targets in remote sensing images have multi-scale characteristics, changeable backgrounds, and complex meteorological characteristics, which lead to low accuracy, false detection, and missed detection of small target ships. In response to the above situation, an improved small-target ship detection model based on YOLOv5s is proposed. First, in order to solve the problems of scale changes and background variability in ship detection, the adaptive spatial feature fusion (ASFF) module was introduced. Secondly, in order to reduce the calculation amount and parameter amount of the detection network, the BoTNet attention mechanism was introduced, and then in order to improve the overall network To improve the detection accuracy, the EIoU border loss function is used, and finally the Slim-neck network is introduced to ensure the overall lightweight of the network. Experiments show that on the main data set LEVIR-Ship, compared with the benchmark YOLOv5s, mAp@0.5 increased by 7.1% to 81.3%, the number of parameters was reduced by 0.44M, the calculation amount was reduced by 0.6GFLOPs, and the weight was reduced by 0.9M . The proposed method performs better in various key indicators and achieves high-precision small target ship detection in complex environments. Comparative experiments are conducted on the verification data set McShips. The experiments show that the proposed method still performs better, verifying the universal applicability of the proposed method.

    参考文献
    相似文献
    引证文献
引用本文

李志昂,周绍发,肖小玲. 基于改进的YOLOv5s小目标船舶遥感图像检测[J]. 科学技术与工程, , ():

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:2023-11-14
  • 最后修改日期:2024-05-24
  • 录用日期:2024-06-05
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注