Scalable Kernel Correlation Filter with Sparse Feature Integration

Abstract

Correlation filters for long-term visual object tracking have recently seen great interest. Although they present competitive performance results, there is still a need for improving their tracking capabilities. In this paper, we present a fast scalable solution based on the Kernalized Correlation Filter (KCF) framework. We introduce an adjustable Gaussian window function and a keypoint-based model for scale estimation to deal with the fixed size limitation in the Kernelized Correlation Filter. Furthermore, we integrate the fast HoG descriptors and Intel's Complex Conjugate Symmetric (CCS) packed format to boost the achievable frame rates. We test our solution using the Visual Tracker Benchmark and the VOT Challenge datasets. We evaluate our tracker in terms of precision and success rate, accuracy, robustness and speed. The empirical evaluations demonstrate clear improvements by the proposed tracker over the KCF algorithm while ranking among the top state-of-the-art trackers.