Compression of indoor video sequences using homography-based segmentation

Tae Joon Park; S. Fleishman; D. Cohen-Or; D. Lischinski

doi:10.1109/PCCGA.2000.883952

Compression of indoor video sequences using homography-based segmentation

Tae Joon Park, S. Fleishman, D. Cohen-Or, D. Lischinski

The Rachel and Selim Benin School of Engineering and Computer Science

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

1 Scopus citations

Abstract

We present a new compression algorithm for video sequences of indoor scenes, or more generally, sequences containing mostly planar and near-planar surfaces. Our approach utilizes edge and optical flow information in order to segment selected keyframes into regions of general shape, such that the motion of each region is predicted well by a planar homography. With this kind of motion prediction, the errors between the predicted intermediate frames and the actual ones are very small, and can be compactly encoded. Our results demonstrate significant improvements in the accuracy of the compressed video sequences, compared to standard general purpose video compression.

Original language	American English
Title of host publication	Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000
Editors	Brian A. Barsky, Yoshihisa Shinagawa, Wenping Wang
Publisher	IEEE Computer Society
Pages	290-299 and 450
ISBN (Electronic)	0769508685
DOIs	https://doi.org/10.1109/PCCGA.2000.883952
State	Published - 2000
Event	8th Pacific Conference on Computer Graphics and Applications, PG 2000 - Hong Kong, China Duration: 3 Oct 2000 → 5 Oct 2000

Publication series

Name	Proceedings - Pacific Conference on Computer Graphics and Applications
Volume	2000-January
ISSN (Print)	1550-4085

Conference

Conference	8th Pacific Conference on Computer Graphics and Applications, PG 2000
Country/Territory	China
City	Hong Kong
Period	3/10/00 → 5/10/00

Bibliographical note

Publisher Copyright:
© 2000 IEEE.

Keywords

Broadcasting
Computer science
Image coding
Image storage
Layout
MPEG 4 Standard
Multimedia communication
Transform coding
Video compression
Video sequences

Access to Document

10.1109/PCCGA.2000.883952

Cite this

Park, T. J., Fleishman, S., Cohen-Or, D., & Lischinski, D. (2000). Compression of indoor video sequences using homography-based segmentation. In B. A. Barsky, Y. Shinagawa, & W. Wang (Eds.), Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000 (pp. 290-299 and 450). Article 883952 (Proceedings - Pacific Conference on Computer Graphics and Applications; Vol. 2000-January). IEEE Computer Society. https://doi.org/10.1109/PCCGA.2000.883952

Park, Tae Joon ; Fleishman, S. ; Cohen-Or, D. et al. / Compression of indoor video sequences using homography-based segmentation. Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000. editor / Brian A. Barsky ; Yoshihisa Shinagawa ; Wenping Wang. IEEE Computer Society, 2000. pp. 290-299 and 450 (Proceedings - Pacific Conference on Computer Graphics and Applications).

@inproceedings{b59d78d5595f4b6d8ff0aa7a167ab11b,

title = "Compression of indoor video sequences using homography-based segmentation",

abstract = "We present a new compression algorithm for video sequences of indoor scenes, or more generally, sequences containing mostly planar and near-planar surfaces. Our approach utilizes edge and optical flow information in order to segment selected keyframes into regions of general shape, such that the motion of each region is predicted well by a planar homography. With this kind of motion prediction, the errors between the predicted intermediate frames and the actual ones are very small, and can be compactly encoded. Our results demonstrate significant improvements in the accuracy of the compressed video sequences, compared to standard general purpose video compression.",

keywords = "Broadcasting, Computer science, Image coding, Image storage, Layout, MPEG 4 Standard, Multimedia communication, Transform coding, Video compression, Video sequences",

author = "Park, {Tae Joon} and S. Fleishman and D. Cohen-Or and D. Lischinski",

note = "Publisher Copyright: {\textcopyright} 2000 IEEE.; 8th Pacific Conference on Computer Graphics and Applications, PG 2000 ; Conference date: 03-10-2000 Through 05-10-2000",

year = "2000",

doi = "10.1109/PCCGA.2000.883952",

language = "American English",

series = "Proceedings - Pacific Conference on Computer Graphics and Applications",

publisher = "IEEE Computer Society",

pages = "290--299 and 450",

editor = "Barsky, {Brian A.} and Yoshihisa Shinagawa and Wenping Wang",

booktitle = "Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000",

address = "United States",

}

Park, TJ, Fleishman, S, Cohen-Or, D & Lischinski, D 2000, Compression of indoor video sequences using homography-based segmentation. in BA Barsky, Y Shinagawa & W Wang (eds), Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000., 883952, Proceedings - Pacific Conference on Computer Graphics and Applications, vol. 2000-January, IEEE Computer Society, pp. 290-299 and 450, 8th Pacific Conference on Computer Graphics and Applications, PG 2000, Hong Kong, China, 3/10/00. https://doi.org/10.1109/PCCGA.2000.883952

Compression of indoor video sequences using homography-based segmentation. / Park, Tae Joon; Fleishman, S.; Cohen-Or, D. et al.
Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000. ed. / Brian A. Barsky; Yoshihisa Shinagawa; Wenping Wang. IEEE Computer Society, 2000. p. 290-299 and 450 883952 (Proceedings - Pacific Conference on Computer Graphics and Applications; Vol. 2000-January).

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

TY - GEN

T1 - Compression of indoor video sequences using homography-based segmentation

AU - Park, Tae Joon

AU - Fleishman, S.

AU - Cohen-Or, D.

AU - Lischinski, D.

PY - 2000

Y1 - 2000

N2 - We present a new compression algorithm for video sequences of indoor scenes, or more generally, sequences containing mostly planar and near-planar surfaces. Our approach utilizes edge and optical flow information in order to segment selected keyframes into regions of general shape, such that the motion of each region is predicted well by a planar homography. With this kind of motion prediction, the errors between the predicted intermediate frames and the actual ones are very small, and can be compactly encoded. Our results demonstrate significant improvements in the accuracy of the compressed video sequences, compared to standard general purpose video compression.

AB - We present a new compression algorithm for video sequences of indoor scenes, or more generally, sequences containing mostly planar and near-planar surfaces. Our approach utilizes edge and optical flow information in order to segment selected keyframes into regions of general shape, such that the motion of each region is predicted well by a planar homography. With this kind of motion prediction, the errors between the predicted intermediate frames and the actual ones are very small, and can be compactly encoded. Our results demonstrate significant improvements in the accuracy of the compressed video sequences, compared to standard general purpose video compression.

KW - Broadcasting

KW - Computer science

KW - Image coding

KW - Image storage

KW - Layout

KW - MPEG 4 Standard

KW - Multimedia communication

KW - Transform coding

KW - Video compression

KW - Video sequences

UR - http://www.scopus.com/inward/record.url?scp=84949515911&partnerID=8YFLogxK

U2 - 10.1109/PCCGA.2000.883952

DO - 10.1109/PCCGA.2000.883952

M3 - Conference contribution

AN - SCOPUS:84949515911

T3 - Proceedings - Pacific Conference on Computer Graphics and Applications

SP - 290-299 and 450

BT - Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000

A2 - Barsky, Brian A.

A2 - Shinagawa, Yoshihisa

A2 - Wang, Wenping

PB - IEEE Computer Society

T2 - 8th Pacific Conference on Computer Graphics and Applications, PG 2000

Y2 - 3 October 2000 through 5 October 2000

ER -

Park TJ, Fleishman S, Cohen-Or D, Lischinski D. Compression of indoor video sequences using homography-based segmentation. In Barsky BA, Shinagawa Y, Wang W, editors, Proceedings - 8th Pacific Conference on Computer Graphics and Applications, PG 2000. IEEE Computer Society. 2000. p. 290-299 and 450. 883952. (Proceedings - Pacific Conference on Computer Graphics and Applications). doi: 10.1109/PCCGA.2000.883952

Compression of indoor video sequences using homography-based segmentation

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this