Generalized Kernel-based Visual Tracking

TL;DR

This paper introduces a generalized kernel-based visual tracking method that trains a robust object model using SVMs, improving upon standard mean shift trackers by addressing their limitations.

Contribution

It proposes a novel approach that trains a discriminative object model from large data, integrating SVMs with mean shift tracking for enhanced robustness.

Findings

Improved tracking accuracy over traditional mean shift methods.

Robust object representation learned from extensive data.

Effective integration of SVM classification with iterative optimization.

Abstract

In this work we generalize the plain MS trackers and attempt to overcome standard mean shift trackers' two limitations. It is well known that modeling and maintaining a representation of a target object is an important component of a successful visual tracker. However, little work has been done on building a robust template model for kernel-based MS tracking. In contrast to building a template from a single frame, we train a robust object representation model from a large amount of data. Tracking is viewed as a binary classification problem, and a discriminative classification rule is learned to distinguish between the object and background. We adopt a support vector machine (SVM) for training. The tracker is then implemented by maximizing the classification score. An iterative optimization scheme very similar to MS is derived for this purpose.