Publication
Title
Adversarial optimization scheme for online tracking model adaptation in autonomous systems
Author
Abstract
Online tracking model updating is typically addressed as a regression problem, involving the minimization of the dispersion between the obtained tracker model response maps in each consecutive frame and some target distribution (e.g., Gaussian), using a closed-form solution. Inspired by the recent applications of Generative Adversarial Networks (GANs), we propose to solve this problem with an adversarial optimization scheme, by employing a Generator-Discriminator network pair. That is, the role of the Generator is assigned to the tracking model so that it produces response maps belonging to some target distribution, while an additional discriminator network is trained to identify if the tracker response maps produced by the generator belong to this target distribution, or not. Therefore, the tracker model exploits the discriminator network as an additional information pool about the target distribution. It is shown that this simple addition improves tracking performance in standard benchmark datasets, without significantly hurting training complexity, thus rendering the proposed method suitable for embedded system application such as in autonomous cars and Unmanned Aerial Systems.
Language
English
Source (journal)
Proceedings. - Los Alamitos, Calif, 1994, currens
Source (book)
2021 IEEE International Conference on Image Processing (ICIP), 19-22 September, 2021, Anchorage, AK, USA
Source (series)
IEEE International Conference on Image Processing ICIP
Publication
New york : IEEE Computer Society Press , 2021
ISSN
1522-4880
ISBN
978-1-6654-4115-5
DOI
10.1109/ICIP42928.2021.9506506
Volume/pages
(2021) , p. 3358-3362
ISI
000819455103095
Full text (Publisher's DOI)
UAntwerpen
Publication type
Subject
External links
Web of Science
Record
Identifier
Creation 17.10.2023
Last edited 27.11.2023
To cite this reference