Online Unsupervised Feature Learning for Visual Tracking

TL;DR

This paper introduces a simple yet effective online unsupervised feature learning framework for visual tracking, outperforming state-of-the-art methods by capturing appearance changes through dictionary learning and spatial pooling.

Contribution

It presents a novel online feature learning pipeline integrated into a tracking-by-detection framework, demonstrating superior performance and flexibility in visual tracking tasks.

Findings

Outperforms all tested state-of-the-art trackers

Effective in capturing appearance and background changes

Flexible integration with existing tracking methods

Abstract

Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications. Here we propose to use the feature learning pipeline for visual tracking. Tracking is implemented using tracking-by-detection and the resulted framework is very simple yet effective. First, online dictionary learning is used to build a dictionary, which captures the appearance changes of the tracking target as well as the background changes. Given a test image window, we extract local image patches from it and each local patch is encoded with respect to the dictionary. The encoded features are then pooled over a spatial pyramid to form an aggregated feature vector. Finally, a simple linear classifier is trained on these features. Our experiments show that the proposed powerful---albeit simple---tracker, outperforms all the state-of-the-art tracking methods that we have tested. Moreover, we evaluate the performance of different dictionary learning and feature encoding methods in the proposed tracking framework, and analyse the impact of each component in the tracking scenario. We also demonstrate the flexibility of feature learning by plugging it into Hare et al.'s tracking method. The outcome is, to our knowledge, the best tracker ever reported, which facilitates the advantages of both feature learning and structured output prediction.