Online learning and fusion of orientation appearance models for robust rigid object tracking

作者:

Highlights:

• Robust learning and fusing of orientation appearance models.

• Combination of image gradient orientations with the directions of surface normals.

• Use of a robust kernel based on the Euler representation of angles.

• Performing 2D plus 3D rigid object tracking, achieving robust performance.

摘要

•Robust learning and fusing of orientation appearance models.•Combination of image gradient orientations with the directions of surface normals.•Use of a robust kernel based on the Euler representation of angles.•Performing 2D plus 3D rigid object tracking, achieving robust performance.

论文关键词:Rigid object tracking,Fusion of orientation appearance models,Subspace learning,Online learning,Face analysis,RGB-D

论文评审过程:Received 5 June 2013, Revised 14 February 2014, Accepted 5 April 2014, Available online 20 May 2014.

论文官网地址:https://doi.org/10.1016/j.imavis.2014.04.017