Tracking Completion

TL;DR

This paper introduces a novel tracking method that combines global subspace models and local pixel observations using matrix completion, improving robustness and accuracy in challenging video sequences.

Contribution

It proposes a new integrated tracking framework that leverages rank-minimization and matrix completion to effectively combine global and local target information.

Findings

Outperforms state-of-the-art trackers on challenging sequences

Effectively integrates global and local models for robust tracking

Demonstrates improved accuracy and robustness in experiments

Abstract

A fundamental component of modern trackers is an online learned tracking model, which is typically modeled either globally or locally. The two kinds of models perform differently in terms of effectiveness and robustness under different challenging situations. This work exploits the advantages of both models. A subspace model, from a global perspective, is learned from previously obtained targets via rank-minimization to address the tracking, and a pixel-level local observation is leveraged si- multaneously, from a local point of view, to augment the subspace model. A matrix completion method is employed to integrate the two models. Unlike previous tracking methods, which locate the target among all fully observed target candidates, the proposed approach first estimates an expected target via the matrix completion through partially observed target candidates, and then, identifies the target according to the estimation accuracy with respect to the target candidates. Specifically, the tracking is formulated as a problem of target appearance estimation. Extensive experiments on various challenging video sequences verify the effectiveness of the proposed approach and demonstrate that the proposed tracker outperforms other popular state-of-the-art trackers.