Improving the Optical Flow Accuracy Based on the Total Variation of Local-Global method

被引:0
|
作者
Zhang, Yugui [1 ]
Fan, Haonan [1 ]
Zheng, Jin [1 ]
Zhang, Chi [1 ]
机构
[1] Beihang Univ, Beijing Key Lab Digital Media, Beijing 100191, Peoples R China
基金
中国国家自然科学基金;
关键词
Optical flow estimation; Total variation; Combined local-global; Median filtering; SEGMENTATION; FIELDS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The aim of this paper is to improve the optical flow accuracy for the preservation of flow discontinuities in total variation method. The proposed method is based on the total variation of the local-global method, including the following steps: firstly, the initial optical flow is obtained from the local-global method; secondly, the data item and the smoothing item are designed based on initial optical flow by using the total variation, with the data item involving the brightness constancy and the gradient constancy, and the smoothing item involving exponential function; and finally, the optical flow results from the second step are optimized by using median filtering. The experimental results show that our proposed method could enhance the accuracy and robustness of the optical flow on the Middlebury Dataset and the MPI Sintel Dataset.
引用
收藏
页码:4658 / 4664
页数:7
相关论文
共 50 条
  • [41] ADC-CPANet:A remote sensing image classification method based on local-global feature fusion
    Wang, Wei
    Li, Xijie
    Wang, Xin
    National Remote Sensing Bulletin, 2024, 28 (10) : 2661 - 2672
  • [42] Principles of biological organization: Local-global negotiation based on "material cause"
    Gunji, Yukio-Pegio
    Haruna, Taichi
    Sawa, Koji
    PHYSICA D-NONLINEAR PHENOMENA, 2006, 219 (02) : 152 - 167
  • [43] Loop closure detection based on local-global similarity measurement strategies
    Dian, Songyi
    Yin, Yanjie
    Wu, Chao
    Zhong, Yuzhong
    Zhang, Hong
    Yuan, Haobin
    JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (02)
  • [44] Local-Global based Deep Registration Neural Network for Rigid Alignment
    Villena-Martinez, Victor
    Saval-Calvo, Marcelo
    Azorin-Lopez, Jorge
    Fuster-Guillo, Andres
    Fisher, Robert B.
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [45] Allele frequency calibration for SNP based genotyping of DNA pools: A regression based local-global error fusion method
    Rahman, Ashfaqur
    Hellicar, Andrew
    Smith, Daniel
    Henshall, John M.
    COMPUTERS IN BIOLOGY AND MEDICINE, 2015, 61 : 48 - 55
  • [46] A Novel Local-Global Graph Convolutional Method for Point Cloud Semantic Segmentation
    Du, Zijin
    Ye, Hailiang
    Cao, Feilong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (04) : 4798 - 4812
  • [47] Refined plastic hinge method for steel frames with local-global interactive buckling
    Zhou, Yi
    Ning, Shuncheng
    Huang, Dongchuan
    Li, Yinglei
    THIN-WALLED STRUCTURES, 2022, 181
  • [48] Local-Global Spatial-Temporal Graph Convolutional Network for Traffic Flow Forecasting
    Zong, Xinlu
    Chen, Zhen
    Yu, Fan
    Wei, Siwei
    ELECTRONICS, 2024, 13 (03)
  • [49] Local-global normality learning and discrepancy normalizing flow for unsupervised image anomaly detection
    Yao, Haiming
    Luo, Wei
    Zhang, Weihang
    Zhang, Xiaotian
    Qiang, Zhenfeng
    Luo, Donghao
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 137
  • [50] Integration of local-global upscaling and grid adaptivity for simulation of subsurface flow in heterogeneous formations
    Gerritsen, M.
    Lambers, J. V.
    COMPUTATIONAL GEOSCIENCES, 2008, 12 (02) : 193 - 208