Discussion among Different Methods of Updating Model Filter in Object Tracking

TL;DR

This paper compares various methods of updating model filters in discriminative correlation filter-based object tracking, analyzing their relationships, differences, and effects through experiments and visualizations.

Contribution

It provides a comprehensive analysis of different filter updating strategies in DCF-based tracking, clarifying their relationships and differences.

Findings

Different updating methods have distinct effects on tracking performance.

The relationship between high-dimensional, frequency, and spatial domain updates is clarified.

Experimental results validate the theoretical analysis and visualizations.

Abstract

Discriminative correlation filters (DCF) have recently shown excellent performance in visual object tracking area. In this paper, we summarize the methods of updating model filter from discriminative correlation filter (DCF) based tracking algorithms and analyzes similarities and differences among these methods. We deduce the relationship between updating coefficient in high dimension (kernel trick), updating filter in frequency domain and updating filter in spatial domain, and analyze the difference among these different ways. We also analyze the difference between the updating filter directly and updating filter's numerator (object response power) with updating filter's denominator (filter's power). The experiments about comparing different updating methods and visualizing the template filters are used to prove our derivation.