Learning Rotation for Kernel Correlation Filter

Abstract

Kernel Correlation Filters have shown a very promising scheme for visual tracking in terms of speed and accuracy on several benchmarks. However it suffers from problems that affect its performance like occlusion, rotation and scale change. This paper tries to tackle the problem of rotation by reformulating the optimization problem for learning the… (More)

Topics

11 Figures and Tables

Cite this paper

@article{Hamdi2017LearningRF, title={Learning Rotation for Kernel Correlation Filter}, author={Abdullah Hamdi and Bernard Ghanem}, journal={CoRR}, year={2017}, volume={abs/1708.03698} }