Video object extraction using feature matching based on nonlocal matting

Meidya Koeshardianto; Eko Mulyanto Yuniarno; Mochamad Hariadi

doi:10.1109/ISITIA.2016.7828658

Video object extraction using feature matching based on nonlocal matting

Meidya Koeshardianto
, Eko Mulyanto Yuniarno
, Mochamad Hariadi

Institut Teknologi Sepuluh Nopember

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Video object extraction is used for extracting foreground and background object from still image or video sequences. We proposed a new method extract an object from image or video sequences with nonlocal matting. One of disadvantages in nonlocal matting is user need to determine manually scribbles to specify foreground and background. To reduce a cost in this process, we add one more step using feature matching based on SIFT algorithm. SIFT is used to identify scribbles automatically based on similarity in image template that provided before. We try to extract objects from video which consist 80 image sequences. Our experiment by using this proposed method show a good result with θ = 0, 05.

Original language	English
Title of host publication	Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016
Subtitle of host publication	Recent Trends in Intelligent Computational Technologies for Sustainable Energy
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	201-206
Number of pages	6
ISBN (Electronic)	9781509017096
DOIs	https://doi.org/10.1109/ISITIA.2016.7828658
Publication status	Published - 20 Jan 2017
Event	2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016 - Lombok, Indonesia Duration: 28 Jul 2016 → 30 Jul 2016

Publication series

Name	Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy

Conference

Conference	2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016
Country/Territory	Indonesia
City	Lombok
Period	28/07/16 → 30/07/16

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Automatic Scribbling
Feature Matching
Image Matting
Non-local Matting
SIFT

Access to Document

10.1109/ISITIA.2016.7828658

Cite this

Koeshardianto, M., Yuniarno, E. M., & Hariadi, M. (2017). Video object extraction using feature matching based on nonlocal matting. In Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy (pp. 201-206). Article 7828658 (Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISITIA.2016.7828658

Koeshardianto, Meidya ; Yuniarno, Eko Mulyanto ; Hariadi, Mochamad. / Video object extraction using feature matching based on nonlocal matting. Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 201-206 (Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy).

@inproceedings{7ed3df3755dd430182aa1bdefbbad7ac,

title = "Video object extraction using feature matching based on nonlocal matting",

abstract = "Video object extraction is used for extracting foreground and background object from still image or video sequences. We proposed a new method extract an object from image or video sequences with nonlocal matting. One of disadvantages in nonlocal matting is user need to determine manually scribbles to specify foreground and background. To reduce a cost in this process, we add one more step using feature matching based on SIFT algorithm. SIFT is used to identify scribbles automatically based on similarity in image template that provided before. We try to extract objects from video which consist 80 image sequences. Our experiment by using this proposed method show a good result with θ = 0, 05.",

keywords = "Automatic Scribbling, Feature Matching, Image Matting, Non-local Matting, SIFT",

author = "Meidya Koeshardianto and Yuniarno, \{Eko Mulyanto\} and Mochamad Hariadi",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016 ; Conference date: 28-07-2016 Through 30-07-2016",

year = "2017",

month = jan,

day = "20",

doi = "10.1109/ISITIA.2016.7828658",

language = "English",

series = "Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "201--206",

booktitle = "Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016",

address = "United States",

}

Koeshardianto, M, Yuniarno, EM & Hariadi, M 2017, Video object extraction using feature matching based on nonlocal matting. in Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy., 7828658, Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy, Institute of Electrical and Electronics Engineers Inc., pp. 201-206, 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016, Lombok, Indonesia, 28/07/16. https://doi.org/10.1109/ISITIA.2016.7828658

Video object extraction using feature matching based on nonlocal matting. / Koeshardianto, Meidya; Yuniarno, Eko Mulyanto ; Hariadi, Mochamad.
Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy. Institute of Electrical and Electronics Engineers Inc., 2017. p. 201-206 7828658 (Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Video object extraction using feature matching based on nonlocal matting

AU - Koeshardianto, Meidya

AU - Yuniarno, Eko Mulyanto

AU - Hariadi, Mochamad

PY - 2017/1/20

Y1 - 2017/1/20

N2 - Video object extraction is used for extracting foreground and background object from still image or video sequences. We proposed a new method extract an object from image or video sequences with nonlocal matting. One of disadvantages in nonlocal matting is user need to determine manually scribbles to specify foreground and background. To reduce a cost in this process, we add one more step using feature matching based on SIFT algorithm. SIFT is used to identify scribbles automatically based on similarity in image template that provided before. We try to extract objects from video which consist 80 image sequences. Our experiment by using this proposed method show a good result with θ = 0, 05.

AB - Video object extraction is used for extracting foreground and background object from still image or video sequences. We proposed a new method extract an object from image or video sequences with nonlocal matting. One of disadvantages in nonlocal matting is user need to determine manually scribbles to specify foreground and background. To reduce a cost in this process, we add one more step using feature matching based on SIFT algorithm. SIFT is used to identify scribbles automatically based on similarity in image template that provided before. We try to extract objects from video which consist 80 image sequences. Our experiment by using this proposed method show a good result with θ = 0, 05.

KW - Automatic Scribbling

KW - Feature Matching

KW - Image Matting

KW - Non-local Matting

KW - SIFT

UR - https://www.scopus.com/pages/publications/85016804148

U2 - 10.1109/ISITIA.2016.7828658

DO - 10.1109/ISITIA.2016.7828658

M3 - Conference contribution

AN - SCOPUS:85016804148

T3 - Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy

SP - 201

EP - 206

BT - Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016

Y2 - 28 July 2016 through 30 July 2016

ER -

Koeshardianto M, Yuniarno EM , Hariadi M. Video object extraction using feature matching based on nonlocal matting. In Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy. Institute of Electrical and Electronics Engineers Inc. 2017. p. 201-206. 7828658. (Proceeding - 2016 International Seminar on Intelligent Technology and Its Application, ISITIA 2016: Recent Trends in Intelligent Computational Technologies for Sustainable Energy). doi: 10.1109/ISITIA.2016.7828658

Video object extraction using feature matching based on nonlocal matting

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this