基于深度卷积神经网络的舰载机轮廓关键点检测算法
作者:
基金项目:

军队科研基金(舰载机自动牵引关键技术研究)


Detection Algorithm of Contour Key Point of Shipboard Aircraft Based on Deep Convolutioanal Neural Network
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    为解决航母舰载机已有关键点检测算法的检测性能不高且对遮挡关键点检测效果差的问题,提出一种基 于深度残差网络和特征金字塔网络的舰载机轮廓关键点检测算法。通过提取舰载机关键点深层图像特征及对不同尺 度的特征进行融合,实验分析目标检测算法、特征提取网络和输入图像大小等因素对关键点检测算法性能的影响, 并与其他关键点检测算法进行实验对比。结果表明,该算法能取得最优效果。

    Abstract:

    In order to solve the problem that the existing key point detection algorithm of carrier aircraft has low detection performance and poor detection effect on key point occlusion, a key point detection algorithm of carrier aircraft contour based on deep residual network and feature pyramid network is proposed. By extracting the deep image features of the key point of the carrier aircraft and fusing the features of different scales, the experiment analyzes the influence of the object detection algorithm, the feature extraction network and the size of the input image on the performance of the key point detection algorithm, and compares it with other key point detection algorithms perform by experimental comparison. The results show that the algorithm can achieve the optimal results.

    参考文献
    相似文献
    引证文献
引用本文

朱兴动.基于深度卷积神经网络的舰载机轮廓关键点检测算法[J].,2021,40(6).

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:2021-02-25
  • 最后修改日期:2021-03-28
  • 在线发布日期: 2021-07-02
文章二维码