Learning Rotation for Kernel Correlation Filter

TL;DR

This paper introduces RKCF, a method that improves Kernel Correlation Filter-based visual tracking by incorporating rotation learning, leading to better accuracy during occlusion, rotation, and scale changes with minimal extra computation.

Contribution

It reformulates the optimization for correlation filters to include rotation learning, enhancing tracking robustness against rotation changes.

Findings

Improved accuracy on OBT50 benchmark videos.

Effective rotation estimation using circulant HOG features.

Minimal additional computational cost.

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 correlation filter. This modification (RKCF) includes learning rotation filter that utilizes circulant structure of HOG feature to guesstimate rotation from one frame to another and enhance the detection of KCF. Hence it gains boost in overall accuracy in many of OBT50 detest videos with minimal additional computation.