Rotation-aware dynamic temporal consistency with spatial sparsity correlation tracking
作者:
Highlights:
• Dynamic temporal modeling can make the filter highlight the ever-changing region.
• Dynamic temporal consistency modeling and spatial sparsity are incorporated in a unified optimization learning model.
• The connected hyper ellipse fitting strategy tries to achieve the optimal rotation angle.
• Comprehensive experiments have fully demonstrated the superior performance of our proposed method.
摘要
•Dynamic temporal modeling can make the filter highlight the ever-changing region.•Dynamic temporal consistency modeling and spatial sparsity are incorporated in a unified optimization learning model.•The connected hyper ellipse fitting strategy tries to achieve the optimal rotation angle.•Comprehensive experiments have fully demonstrated the superior performance of our proposed method.
论文关键词:Dynamic temporal consistency,Spatial sparsity,Correlation tracking,Rotation invariance,Connected hyper ellipse fitting
论文评审过程:Received 26 May 2022, Revised 8 August 2022, Accepted 26 August 2022, Available online 5 September 2022, Version of Record 19 September 2022.
论文官网地址:https://doi.org/10.1016/j.imavis.2022.104546