Fast Tracking via Spatio-Temporal Context Learning

TL;DR

This paper introduces a fast, robust visual tracking algorithm that leverages spatio-temporal context and Bayesian modeling, achieving high speed and accuracy suitable for real-time applications.

Contribution

It presents a novel spatio-temporal context learning approach using Bayesian framework and FFT for rapid, robust tracking, outperforming existing methods in speed and accuracy.

Findings

Runs at 350 fps on standard hardware

Performs favorably against state-of-the-art methods

Offers a robust and efficient tracking solution

Abstract

In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context based on a Bayesian framework, which models the statistical correlation between the low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is posed by computing a confidence map, and obtaining the best target location by maximizing an object location likelihood function. The Fast Fourier Transform is adopted for fast learning and detection in this work. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.