CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking

How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking scenarios. Instead, long-term tracking settings have been subst...

Full description

Saved in:
Bibliographic Details
Published in2022 26th International Conference on Pattern Recognition (ICPR) pp. 5132 - 5139
Main Authors Dunnhofer, Matteo, Machine, Christian Micheloni
Format Conference Proceeding
LanguageEnglish
Published IEEE 21.08.2022
Subjects
Behavioral sciences
Benchmark testing
Deep learning
Location awareness
Pattern recognition
Target tracking
Visualization
Online AccessGet full text

Cover

More Information
Summary:How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking scenarios. Instead, long-term tracking settings have been substantially ignored by the solutions. In this paper, we explicitly consider long-term tracking scenarios and provide a framework, named CoCoLoT, that combines the characteristics of complementary visual trackers to achieve enhanced long-term tracking performance. CoCoLoT perceives whether the trackers are following the target object through an online learned deep verification model, and accordingly activates a decision policy which selects the best performing tracker as well as it corrects the performance of the failing one. The proposed methodology is evaluated extensively and the comparison with several other solutions reveals that it competes favourably with the state-of-the-art on the most popular long-term visual tracking benchmarks.
ISSN:2831-7475
DOI:10.1109/ICPR56361.2022.9956082