Deep Convolutional Particle Filter with Adaptive Correlation Maps for Visual Tracking

Authors

Reza Jilil Mozhdehi, Marquette University
Yevgeniy Vladimirovich Reznichenko, Marquette University
Abubakar Siddique, Marquette University
Henry P. Medeiros, Marquette UniversityFollow

Document Type

Article

Language

eng

Publication Date

2018

Publisher

Institute of Electrical and Electronic Engineers (IEEE)

Source Publication

2018 25th IEEE International Conference on Image Processing (ICIP)

Source ISSN

2381-8549

Original Item ID

DOI: 10.1109/ICIP.2018.8451069

Abstract

The robustness of the visual trackers based on the correlation maps generated from convolutional neural networks can be substantially improved if these maps are used to employed in conjunction with a particle filter. In this article, we present a particle filter that estimates the target size as well as the target position and that utilizes a new adaptive correlation filter to account for potential errors in the model generation. Thus, instead of generating one model which is highly dependent on the estimated target position and size, we generate a variable number of target models based on high likelihood particles, which increases in challenging situations and decreases in less complex scenarios. Experimental results on the Visual Tracker Benchmark vl.0 demonstrate that our proposed framework significantly outperforms state-of-the-art methods.

Comments

Accepted version. 2018 25th IEEE International Conference on Image Processing (ICIP), (2018): 798-802. DOI. © 2018 Institute of Electrical and Electronic Engineers (IEEE). Used with permission.

Recommended Citation

Mozhdehi, Reza Jilil; Reznichenko, Yevgeniy Vladimirovich; Siddique, Abubakar; and Medeiros, Henry P., "Deep Convolutional Particle Filter with Adaptive Correlation Maps for Visual Tracking" (2018). Electrical and Computer Engineering Faculty Research and Publications. 545.
https://epublications.marquette.edu/electric_fac/545