Visual object tracking using adaptive correlation filters

TLDR

Correlation filters can track complex objects at high speed, yet older template methods fail and modern approaches such as ASEF and UMACE are poorly suited for tracking due to their training demands. Visual tracking requires robust filters that can be trained from a single frame and dynamically adapted as the target appearance changes. The authors introduce the MOSSE filter, which yields stable correlation filters from a single frame, and detect occlusion via peak‑to‑sidelobe ratio to pause and resume tracking. The MOSSE‑based tracker remains robust to lighting, scale, pose, and nonrigid deformations while running at 669 fps.

Abstract

Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of-the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. A tracker based upon MOSSE filters is robust to variations in lighting, scale, pose, and nonrigid deformations while operating at 669 frames per second. Occlusion is detected based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears.