Staple: Complementary Learners for Real-Time Tracking

TL;DR

This paper introduces Staple, a real-time tracker combining correlation filters and color cues, which outperforms existing methods in benchmarks by leveraging complementary features for robust object tracking.

Contribution

The paper proposes a simple, fast, and effective tracking framework that integrates correlation filters with color information in a ridge regression model, achieving state-of-the-art performance.

Findings

Operates at over 80 FPS.

Outperforms all entries in VOT14 competition.

Surpasses recent sophisticated trackers in benchmarks.

Abstract

Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes. However, since the model that they learn depends strongly on the spatial layout of the tracked object, they are notoriously sensitive to deformation. Models based on colour statistics have complementary traits: they cope well with variation in shape, but suffer when illumination is not consistent throughout a sequence. Moreover, colour distributions alone can be insufficiently discriminative. In this paper, we show that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.