Feature based video stabilization based on boosted HAAR Cascade and representative point matching algorithm

作者：

Highlights：

• Video capturing needs an improved video stabilization.

• Videos often contain many foregrounds facial.

• The feature-based tracking of object improves motion estimation accuracy.

• A smoother sequence after the motion compensation is developed.

• It also improved the robustness, precision and quality of the video.

摘要

•Video capturing needs an improved video stabilization.•Videos often contain many foregrounds facial.•The feature-based tracking of object improves motion estimation accuracy.•A smoother sequence after the motion compensation is developed.•It also improved the robustness, precision and quality of the video.

论文关键词：Digital image stabilization,Representative point matching,Boosted HAAR Cascade,Foreground feature selection,Motion compensation

论文评审过程：Received 7 February 2020, Revised 16 April 2020, Accepted 31 May 2020, Available online 13 June 2020, Version of Record 30 June 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.103957