Learning Rotation for Kernel Correlation Filter
This addresses rotation issues in visual tracking for applications like surveillance, but it is incremental as it modifies an existing method.
The paper tackles the problem of rotation in Kernel Correlation Filter tracking by reformulating the optimization to learn a rotation filter, resulting in a boost in overall accuracy on OBT50 videos with minimal additional computation.
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.