Visual object tracking using adaptive correlation filters

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 trackin...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 2544 - 2550
Main Authors Bolme, David S, Beveridge, J Ross, Draper, Bruce A, Yui Man Lui
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Adaptive filters
Cameras
Convolution
Detectors
Object detection
Resumes
Robustness
Target tracking
Video sequences
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:1424469848
9781424469840
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2010.5539960