Illumination invariant motion estimation and segmentation

Yeonho Kim; Sooyeong Yi

doi:10.1007/978-3-642-27186-1_10

Illumination invariant motion estimation and segmentation

Yeonho Kim, Sooyeong Yi

Dept. of Electrical and Information Engineering

Samsung

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

2 Scopus citations

Abstract

Extracting moving objects from their background or partitioning them have been one of the most prerequisite tasks for various computer vision applications such as surveillance, tracking, human machine interface, etc. Though many previous approaches have been working in a certain level, still they are not robust under various unexpected situation such as large illumination change. In this paper, we propose a motion segmentation method based on our robust illumination invariant optical flow estimation. We present the superiority of our motion estimation method with synthesized images and improved segmentation results with real images.

Original language	English
Title of host publication	Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.
Pages	78-87
Number of pages	10
Edition	PART 2
DOIs	https://doi.org/10.1007/978-3-642-27186-1_10
State	Published - 2011
Event	2011 International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011, in Conjunction with GDC 2011 - Jeju Island, Korea, Republic of Duration: 8 Dec 2011 → 10 Dec 2011

Publication series

Name	Communications in Computer and Information Science
Number	PART 2
Volume	263 CCIS
ISSN (Print)	1865-0929

Conference

Conference	2011 International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011, in Conjunction with GDC 2011
Country/Territory	Korea, Republic of
City	Jeju Island
Period	8/12/11 → 10/12/11

Keywords

Illumination invariant
Motion estimation
Optical flow
Segmentation

Access to Document

10.1007/978-3-642-27186-1_10

Cite this

Kim, Y., & Yi, S. (2011). Illumination invariant motion estimation and segmentation. In Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc. (PART 2 ed., pp. 78-87). (Communications in Computer and Information Science; Vol. 263 CCIS, No. PART 2). https://doi.org/10.1007/978-3-642-27186-1_10

Kim, Yeonho ; Yi, Sooyeong. / Illumination invariant motion estimation and segmentation. Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.. PART 2. ed. 2011. pp. 78-87 (Communications in Computer and Information Science; PART 2).

@inproceedings{8bb5d405f9f649808dade30ac67ef737,

title = "Illumination invariant motion estimation and segmentation",

abstract = "Extracting moving objects from their background or partitioning them have been one of the most prerequisite tasks for various computer vision applications such as surveillance, tracking, human machine interface, etc. Though many previous approaches have been working in a certain level, still they are not robust under various unexpected situation such as large illumination change. In this paper, we propose a motion segmentation method based on our robust illumination invariant optical flow estimation. We present the superiority of our motion estimation method with synthesized images and improved segmentation results with real images.",

keywords = "Illumination invariant, Motion estimation, Optical flow, Segmentation",

author = "Yeonho Kim and Sooyeong Yi",

year = "2011",

doi = "10.1007/978-3-642-27186-1\_10",

language = "English",

isbn = "9783642271854",

series = "Communications in Computer and Information Science",

number = "PART 2",

pages = "78--87",

booktitle = "Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.",

edition = "PART 2",

note = "2011 International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011, in Conjunction with GDC 2011 ; Conference date: 08-12-2011 Through 10-12-2011",

}

Kim, Y & Yi, S 2011, Illumination invariant motion estimation and segmentation. in Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.. PART 2 edn, Communications in Computer and Information Science, no. PART 2, vol. 263 CCIS, pp. 78-87, 2011 International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011, in Conjunction with GDC 2011, Jeju Island, Korea, Republic of, 8/12/11. https://doi.org/10.1007/978-3-642-27186-1_10

Illumination invariant motion estimation and segmentation. / Kim, Yeonho; Yi, Sooyeong.
Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.. PART 2. ed. 2011. p. 78-87 (Communications in Computer and Information Science; Vol. 263 CCIS, No. PART 2).

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

TY - GEN

T1 - Illumination invariant motion estimation and segmentation

AU - Kim, Yeonho

AU - Yi, Sooyeong

PY - 2011

Y1 - 2011

N2 - Extracting moving objects from their background or partitioning them have been one of the most prerequisite tasks for various computer vision applications such as surveillance, tracking, human machine interface, etc. Though many previous approaches have been working in a certain level, still they are not robust under various unexpected situation such as large illumination change. In this paper, we propose a motion segmentation method based on our robust illumination invariant optical flow estimation. We present the superiority of our motion estimation method with synthesized images and improved segmentation results with real images.

AB - Extracting moving objects from their background or partitioning them have been one of the most prerequisite tasks for various computer vision applications such as surveillance, tracking, human machine interface, etc. Though many previous approaches have been working in a certain level, still they are not robust under various unexpected situation such as large illumination change. In this paper, we propose a motion segmentation method based on our robust illumination invariant optical flow estimation. We present the superiority of our motion estimation method with synthesized images and improved segmentation results with real images.

KW - Illumination invariant

KW - Motion estimation

KW - Optical flow

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84055217095&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-27186-1_10

DO - 10.1007/978-3-642-27186-1_10

M3 - Conference contribution

AN - SCOPUS:84055217095

SN - 9783642271854

T3 - Communications in Computer and Information Science

SP - 78

EP - 87

BT - Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.

T2 - 2011 International Conference on Multimedia, Computer Graphics and Broadcasting, MulGraB 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011, in Conjunction with GDC 2011

Y2 - 8 December 2011 through 10 December 2011

ER -

Kim Y, Yi S. Illumination invariant motion estimation and segmentation. In Multimedia, Computer Graphics and Broadcasting - Int. Conference, MulGraB 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, in Conjunction with GDC 2011, Proc.. PART 2 ed. 2011. p. 78-87. (Communications in Computer and Information Science; PART 2). doi: 10.1007/978-3-642-27186-1_10

Illumination invariant motion estimation and segmentation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this