Kernel Cross-Correlator

TL;DR

The paper introduces a kernel cross-correlator (KCC) that extends traditional linear cross-correlation to a non-linear space using kernel tricks, improving robustness and flexibility in visual perception tasks like tracking and activity recognition.

Contribution

It presents a novel KCC method that unifies correlation filters, supports any kernel, and efficiently predicts transformations without strict data structure limitations.

Findings

KCC improves robustness to noise and distortions.

KCC demonstrates superior performance in visual tracking.

KCC is flexible and computationally efficient.

Abstract

Cross-correlator plays a significant role in many visual perception tasks, such as object detection and tracking. Beyond the linear cross-correlator, this paper proposes a kernel cross-correlator (KCC) that breaks traditional limitations. First, by introducing the kernel trick, the KCC extends the linear cross-correlation to non-linear space, which is more robust to signal noises and distortions. Second, the connection to the existing works shows that KCC provides a unified solution for correlation filters. Third, KCC is applicable to any kernel function and is not limited to circulant structure on training data, thus it is able to predict affine transformations with customized properties. Last, by leveraging the fast Fourier transform (FFT), KCC eliminates direct calculation of kernel vectors, thus achieves better performance yet still with a reasonable computational cost. Comprehensive experiments on visual tracking and human activity recognition using wearable devices demonstrate its robustness, flexibility, and efficiency. The source codes of both experiments are released at https://github.com/wang-chen/KCC