基于改进Monodepth2的内窥镜图像深度估计方法
DOI:
作者:
作者单位:

山东理工大学

作者简介:

通讯作者:

中图分类号:

TP391, R572

基金项目:

国家自然科学基金(62001272)


Depth estimation method of endoscopic image based on improved Monodepth2
Author:
Affiliation:

Shandong University of Technology

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:

    内窥镜图像深度估计是微创手术中的一个重要技术难题。为提高内窥镜图像深度估计的准确性,提出了一种基于改进Monodepth2的内窥镜图像深度估计方法。在深度估计网络中,编码器使用ResNet34模块,并引入SAB注意力机制、改进的FPN模块以及特征增强模块,以使所提网络更好地理解全局信息、灵活有效地处理多尺度特征,并进一步增强其稳定性和可靠性。解码器通过上采样获取图像的深度信息和位姿信息。采用光度重投影误差、结构相似性和边缘感知平滑误差作为损失函数,以进一步提高所提方法的准确性。评估采用Hamlyn公共数据集,实验结果表明本文方法可更加准确地估计内窥镜图像的深度信息,进一步验证了所提方法的有效性和准确性。

    Abstract:

    Endoscopic image depth estimation is an important technical challenge in minimally invasive surgery. In order to improve the accuracy of depth estimation of endoscopic image, an endoscopic image depth estimation method based on improved Monodepth2 is proposed. In the depth estimation network, the encoder used the ResNet34 module and introduced the SAB attention mechanism, the improved FPN module and feature enhancement module, so that the proposed network could better understand the global information, deal with multi-scale features flexibly and effectively, and further enhanced its stability and reliability. The decoder obtained the depth information and pose information of the image through up-sampling. To further improve the accuracy of the proposed method, photometric reprojection error, structural similarity and edge perception smoothing error were used as loss functions. The evaluation uses Hamlyn public dataset, and the experimental results show that the proposed method can estimate the depth information of endoscope image more accurately, which further verifies the effectiveness and accuracy of the proposed method.

    参考文献
    相似文献
    引证文献
引用本文

王晓雨,孟晓亮,张立晔,等. 基于改进Monodepth2的内窥镜图像深度估计方法[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:2023-10-23
  • 最后修改日期:2024-05-27
  • 录用日期:2024-05-29
  • 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