基于改进RetinaNet的遥感图像目标检测算法
DOI:
作者:
作者单位:

1.华东交通大学;2.萍乡学院

作者简介:

通讯作者:

中图分类号:

基金项目:

江西省自然科学基金面上项目(20232BAB203057)


An Object Detection Algorithm for Remote Sensing Images Based on Improved RetinaNet
Author:
Affiliation:

Fund Project:

Jiangxi Provincial Natural Science Foundation General Program Project (20232BAB203057)

  • 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:

    【目的】遥感图像目标检测在智慧交通方面有广泛的应用,如路网运行状态动态监测、道路智慧执法、公路灾害智能监测等。由于遥感图像具有目标小而密集、尺度变化大且以任意方向分布等特点,通用目标检测器直接应用于遥感图像时检测效果不佳。【方法】针对以上挑战,提出了一种基于改进RetinaNet的遥感图像目标检测算法。本文算法结合了下采样块和卷积核动态选择的优势。首先,该模型在基础特征提取网络ResNet50上引入一个改进的下采样模块,对特征进行多种下采样处理,然后采用卷积核选择机制动态选择空间感受野,以此对多尺度的语义信息进行建模,最后得到目标物体的分类和回归结果。【结果】实验结果表明,该方法在大规模遥感图像目标检测数据集DOTA上的平均精度均值比原Retinanet网络提升了3.2%。【结论】通过引入下采样模块和动态选择卷积核大小的机制,本文算法在一定程度上改进了对多尺度遥感目标的识别能力。

    Abstract:

    Remote sensing image object detection has a wide range of applications in intelligent transport, such as dynamic monitoring of road network operation status, intelligent law enforcement on roads, and intelligent monitoring of road disasters. Due to the characteristics of small and dense targets, large scale changes, and arbitrary direction distribution in remote sensing images, general object detectors have poor detection performance when directly applied to remote sensing images. To address these challenges,this paper proposes a remote sensing image object detection algorithm based on improved Retinanet. First, the model introduces Improved Downsampling Module (IDM) on the base feature extraction network ResNet50, which performs multiple down-sampling processing on features, and then dynamically selects the spatial receptive field using the convolution kernel selection mechanism to model the multi-scale semantic information of the scene. Finally, the classification and regression results of the target object are obtained. Experimental results show that the proposed method improves the mAP by 3.2% on the large-scale remote sensing image object detection dataset DOTA compared to the original Retinanet network, enabling more accurate localization and identification of remote sensing targets.

    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:2024-03-07
  • 最后修改日期:2024-04-03
  • 录用日期:2024-04-10
  • 在线发布日期: 2024-06-14
  • 出版日期: