Study on semiautomatic object segmentation technique for 2D/3D conversion
- Authors
- Kim, J.S.; Whangbo, T.K.
- Issue Date
- Jan-2014
- Publisher
- Research India Publications
- Keywords
- Energy function; Grabcut; Object tracking; Segmentation; Snake algorithm; Trimap
- Citation
- International Journal of Applied Engineering Research, v.9, no.24, pp.25347 - 25355
- Journal Title
- International Journal of Applied Engineering Research
- Volume
- 9
- Number
- 24
- Start Page
- 25347
- End Page
- 25355
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/13107
- ISSN
- 0973-4562
- Abstract
- GrabCut Algorithm is an efficient and iterative approach for object segmentation in complex environment with user interaction. But its segmentation results depend on the initial Tripmap specified by the users. in this paper suggests the semiautomatic object segmentation technique for 2D to 3D conversion using GrabCut Algorithm. The suggested method is to perform object segmentation automatically in the next frame after using the result from GrabCut for the first frame in image sequence, and then mat the object region for easy 2D to 3D conversion by using the snake algorithm. When the suggested method is applied, it shows the result of detecting an object more effectively than the existing GrabCut algorithm even when the distribution of foreground and background color is similar. © 2014, Research India Publications.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 컴퓨터공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/13107)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.