Zero-variance minibatch Monte Carlo for pixel-wise visual tracking
- Authors
- Park, J.; Kwon, Junseok
- Issue Date
- 15-Oct-2020
- Publisher
- INST ENGINEERING TECHNOLOGY-IET
- Keywords
- object detection; Monte Carlo methods; target tracking; image representation; image sampling; image resolution; zero-variance minibatch Monte Carlo; pixel-wise visual tracking; pixel-wise posterior estimation; minibatch Monte Carlo sampling; background pixels; noisy bounding box representation; visual tracker
- Citation
- ELECTRONICS LETTERS, v.56, no.21, pp 1118 - 1120
- Pages
- 3
- Journal Title
- ELECTRONICS LETTERS
- Volume
- 56
- Number
- 21
- Start Page
- 1118
- End Page
- 1120
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/43780
- DOI
- 10.1049/el.2020.1900
- ISSN
- 0013-5194
1350-911X
- Abstract
- In this study, the authors present a novel visual tracking method using the pixel-wise posterior estimation and minibatch Monte Carlo sampling. To avoid background pixels in the noisy bounding box representation, they estimate the posteriors in a pixel-wise manner. To boost the pixel-wise posterior estimation, they adopt minibatch Monte Carlo sampling, where only a small portion of pixels are used for inference. Experimental results demonstrate that the proposed visual tracker produces accurate tracking results using a small portion of pixels for the posterior estimation and is comparable to state-of-the-art methods.
- Files in 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.