结合卷积和交叉变换网络的光流估计
CSTR:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP 391.4

基金项目:

国家自然科学基金资助项目(62276167); 上海市自然科学基金资助项目(20ZR1437900)


Convolution and cross transformer network for optical flow estimation
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:

    光流估计是计算机视觉领域的核心任务。近年来,基于深度学习的光流估计方法取得了显著进展。但光流算法容易受到图像遮挡、重叠物体和相似物体的影响,从而导致运动估计准确性下降。为了解决这一问题,提出了一种结合卷积和交叉变换网络的光流估计模型。首先,利用卷积和交叉注意力机制对连续两帧图像进行特征提取与增强。其次,结合上下文特征网络编码提供的上下文信息,通过特征聚合模块产生聚合特征,使用ConvGRU模块进行光流的迭代更新,并通过上采样模块产生光流特征估计图,完成光流估计任务。最后,进行MPI-Sintel 和 KITTI 2015数据集的综合实验对比分析。实验结果表明,所提出的方法可以有效地提高光流估计的精度,并具有良好的泛化性。

    Abstract:

    Optical flow estimation is a core task in the field of computer vision. In recent years, deep learning based optical flow estimation methods have made significant progress. However, optical flow algorithms are easily affected by image occlusion, overlapping objects and similar objects, leading to a decrease in the accuracy of motion estimation. To overcome this problem, an optical flow estimation model combining convolutional and cross transformer network was proposed. Firstly, feature extraction and enhancement were performed on two consecutive frames of images using convolution and cross attention mechanisms. Secondly, combining the contextual information provided by the context feature network encoding, the feature aggregation module was used to generate aggregated features, and the ConvGRU module was used to iteratively update the optical flow. The optical flow feature estimation maps were generated through the upsampling module to complete the optical flow estimation task. Finally, a comprehensive experimental comparative analysis was conducted on the MPI Sintel and KITTI 2015 datasets. The experimental results show that the proposed method could effectively improve the accuracy of optical flow estimation and had good generalization ability.

    参考文献
    相似文献
    引证文献
引用本文

温远斌,黄影平,李瀚灵.结合卷积和交叉变换网络的光流估计[J].上海理工大学学报,2025,47(4):438-448.

复制
分享
相关视频

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:2024-06-06
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2025-09-29
  • 出版日期:
文章二维码