Graph visual tracking using conditional uncertainty minimization and minibatch Monte Carlo inference
- Authors
- Kwon, J.
- Issue Date
- Oct-2021
- Publisher
- Elsevier Inc.
- Keywords
- Conditional uncertainty minimization; Markov network; Minibatch Monte Carlo; Non-nested sampling; Visual tracking
- Citation
- Information Sciences, v.574, pp 363 - 376
- Pages
- 14
- Journal Title
- Information Sciences
- Volume
- 574
- Start Page
- 363
- End Page
- 376
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/48325
- DOI
- 10.1016/j.ins.2021.05.052
- ISSN
- 0020-0255
1872-6291
- Abstract
- In this paper, we propose a novel visual tracking method based on conditional uncertainty minimization (CUM), minibatch Monte Carlo (MMC), and non-nested sampling (NNS). We represent a target as a Markov network with nodes and edges, where each node corresponds to the corresponding pixel of the target and each edge describes the relations among the pixels. The nodes are then grouped into optimal cliques using the proposed CUM, which minimizes the conditional uncertainty (i.e. the variance of the conditional expectation) between two cliques. The aforementioned minimization process is facilitated using the proposed NNS. During visual tracking, Markov networks evolve across frames and describe the geometrically varying appearances of the target. In many cases, these networks cannot represent the targets perfectly; however, the configurations of the target can be inferred accurately using the CUM and the best configuration can be found at an early stage of the Monte Carlo sampling using the proposed MMC. The numerical results demonstrate that our method qualitatively and quantitatively outperforms other state-of-the-art trackers on standard benchmark datasets. In particular, our method accurately tracks deformable objects in realtime.
- 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.