Optimal visual tracking using Wasserstein transport proposals
- Authors
- Hong, J.; Kwon, Junseok
- Issue Date
- Dec-2022
- Publisher
- Elsevier Ltd
- Keywords
- MCMC; Optimal transport; Visual tracking; Wasserstein space
- Citation
- Expert Systems with Applications, v.209
- Journal Title
- Expert Systems with Applications
- Volume
- 209
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/58875
- DOI
- 10.1016/j.eswa.2022.118251
- ISSN
- 0957-4174
1873-6793
- Abstract
- We propose a novel visual tracking method based on the Wasserstein transport proposal (WTP). In this study, we theoretically derive the optimal proposal function in Markov chain Monte Carlo (MCMC) based visual tracking frameworks. For this objective, we adopt the optimal transport theory in the Wasserstein space and present a new transport map that can transform from a simple proposal distribution to the optimal target distribution. To find the best transport map, we conduct an additional Monte Carlo simulation. Experimental results demonstrate that the proposed method outperforms other state-of-the-art visual tracking methods. The proposed WTP can be substituted with conventional proposal functions in an MCMC framework, and thus can be plugged into any existing MCMC-based visual tracker. © 2022 Elsevier Ltd
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.