Adaptive Combination of Local Motion, Appearance, and Shape for Video Segmentation
- Authors
- Shim, Woo-sung; Kim, Se-hoon; Lee, Soochahn
- Issue Date
- Nov-2016
- Publisher
- Society for Imaging Science and Technology
- Keywords
- Video Segmentation; Adaptive Combination; Local Motion; Local Shape; Local Appearance
- Citation
- Journal of Imaging Science and Technology, v.60, no.6
- Journal Title
- Journal of Imaging Science and Technology
- Volume
- 60
- Number
- 6
- URI
- https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/8623
- DOI
- 10.2352/J.ImagingSci.Technol.2016.60.6.060409
- ISSN
- 1062-3701
1943-3522
- Abstract
- In this paper, we propose an accurate and robust video segmentation method. The main contributions are threefold: (1) multiple cues (appearance and shape) are explicitly used and adaptively combined to determine segment probability; (2) motion is implicitly used to compute the shape cue; and (3) the segment labeling is improved by utilizing geodesic graph cuts. Experimental results show the effectiveness of the proposed method. (C) 2016 Society for Imaging Science and Technology.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Department of Electronic Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/8623)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.