In Defense of Subspace Tracker: Orthogonal Embedding for Visual Tracking

TL;DR

This paper introduces a discriminative subspace learning approach for visual tracking that adaptively models target and background, significantly improving tracking accuracy over existing subspace trackers.

Contribution

It proposes a joint learning method to create a dimension-adaptive, discriminative subspace for robust visual tracking, enhancing performance over prior subspace-based methods.

Findings

Achieves over 9% performance improvement compared to state-of-the-art subspace trackers.

Demonstrates competitive results on four popular tracking benchmarks.

Validates the effectiveness of discriminative, adaptive subspace learning in visual tracking.

Abstract

The paper focuses on a classical tracking model, subspace learning, grounded on the fact that the targets in successive frames are considered to reside in a low-dimensional subspace or manifold due to the similarity in their appearances. In recent years, a number of subspace trackers have been proposed and obtained impressive results. Inspired by the most recent results that the tracking performance is boosted by the subspace with discrimination capability learned over the recently localized targets and their immediately surrounding background, this work aims at solving such a problem: how to learn a robust low-dimensional subspace to accurately and discriminatively represent these target and background samples. To this end, a discriminative approach, which reliably separates the target from its surrounding background, is injected into the subspace learning by means of joint learning, achieving a dimension-adaptive subspace with superior discrimination capability. The proposed approach is extensively evaluated and compared with the state-of-the-art trackers on four popular tracking benchmarks. The experimental results demonstrate that the proposed tracker performs competitively against its counterparts. In particular, it achieves more than 9% performance increase compared with the state-of-the-art subspace trackers.