Measuring the motion similarity in video indexing

A. Hanis, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Recent growth in the number of digital videos available motivates the development of video databases for the efficient management of these videos. Common video databases use image information calculated from key frames such as color, texture, shape to index videos, and only few of them are capable to store and retrieve motion information. In this paper we present a method for automatic motion based video indexing and retrieval. A prototype system has been developed, which automatically splits a video into shorter unit called shots, extract representative frames from each shot and estimates motion information in the neighborhood of the r-frame with the phase correlation method. A query can be an extracted motion information of a short sample image sequence, or a quantitatively given motion intensity in five region of the frame.

Original languageEnglish
Title of host publicationProceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages507-512
Number of pages6
Volume2
ISBN (Print)9531840547, 9789531840545
DOIs
Publication statusPublished - 2003
Event4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications, EC-VIP-MC 2003 - Zagreb, Croatia
Duration: Jul 2 2003Jul 5 2003

Other

Other4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications, EC-VIP-MC 2003
CountryCroatia
CityZagreb
Period7/2/037/5/03

Fingerprint

indexing
video
Correlation methods
Textures
Color
management

Keywords

  • Data mining
  • Image databases
  • Image retrieval
  • Indexes
  • Indexing
  • Information retrieval
  • Motion estimation
  • Motion measurement
  • Prototypes
  • Shape

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Communication

Cite this

Hanis, A., & Szirányi, T. (2003). Measuring the motion similarity in video indexing. In Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications (Vol. 2, pp. 507-512). [1220514] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VIPMC.2003.1220514

Measuring the motion similarity in video indexing. / Hanis, A.; Szirányi, T.

Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2003. p. 507-512 1220514.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hanis, A & Szirányi, T 2003, Measuring the motion similarity in video indexing. in Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications. vol. 2, 1220514, Institute of Electrical and Electronics Engineers Inc., pp. 507-512, 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications, EC-VIP-MC 2003, Zagreb, Croatia, 7/2/03. https://doi.org/10.1109/VIPMC.2003.1220514
Hanis A, Szirányi T. Measuring the motion similarity in video indexing. In Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications. Vol. 2. Institute of Electrical and Electronics Engineers Inc. 2003. p. 507-512. 1220514 https://doi.org/10.1109/VIPMC.2003.1220514
Hanis, A. ; Szirányi, T. / Measuring the motion similarity in video indexing. Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2003. pp. 507-512
@inproceedings{058382bbf87548a4a0176b954b2ca6f7,
title = "Measuring the motion similarity in video indexing",
abstract = "Recent growth in the number of digital videos available motivates the development of video databases for the efficient management of these videos. Common video databases use image information calculated from key frames such as color, texture, shape to index videos, and only few of them are capable to store and retrieve motion information. In this paper we present a method for automatic motion based video indexing and retrieval. A prototype system has been developed, which automatically splits a video into shorter unit called shots, extract representative frames from each shot and estimates motion information in the neighborhood of the r-frame with the phase correlation method. A query can be an extracted motion information of a short sample image sequence, or a quantitatively given motion intensity in five region of the frame.",
keywords = "Data mining, Image databases, Image retrieval, Indexes, Indexing, Information retrieval, Motion estimation, Motion measurement, Prototypes, Shape",
author = "A. Hanis and T. Szir{\'a}nyi",
year = "2003",
doi = "10.1109/VIPMC.2003.1220514",
language = "English",
isbn = "9531840547",
volume = "2",
pages = "507--512",
booktitle = "Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Measuring the motion similarity in video indexing

AU - Hanis, A.

AU - Szirányi, T.

PY - 2003

Y1 - 2003

N2 - Recent growth in the number of digital videos available motivates the development of video databases for the efficient management of these videos. Common video databases use image information calculated from key frames such as color, texture, shape to index videos, and only few of them are capable to store and retrieve motion information. In this paper we present a method for automatic motion based video indexing and retrieval. A prototype system has been developed, which automatically splits a video into shorter unit called shots, extract representative frames from each shot and estimates motion information in the neighborhood of the r-frame with the phase correlation method. A query can be an extracted motion information of a short sample image sequence, or a quantitatively given motion intensity in five region of the frame.

AB - Recent growth in the number of digital videos available motivates the development of video databases for the efficient management of these videos. Common video databases use image information calculated from key frames such as color, texture, shape to index videos, and only few of them are capable to store and retrieve motion information. In this paper we present a method for automatic motion based video indexing and retrieval. A prototype system has been developed, which automatically splits a video into shorter unit called shots, extract representative frames from each shot and estimates motion information in the neighborhood of the r-frame with the phase correlation method. A query can be an extracted motion information of a short sample image sequence, or a quantitatively given motion intensity in five region of the frame.

KW - Data mining

KW - Image databases

KW - Image retrieval

KW - Indexes

KW - Indexing

KW - Information retrieval

KW - Motion estimation

KW - Motion measurement

KW - Prototypes

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=84874807098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874807098&partnerID=8YFLogxK

U2 - 10.1109/VIPMC.2003.1220514

DO - 10.1109/VIPMC.2003.1220514

M3 - Conference contribution

AN - SCOPUS:84874807098

SN - 9531840547

SN - 9789531840545

VL - 2

SP - 507

EP - 512

BT - Proceedings EC-VIP-MC 2003 - 4th EURASIP Conference Focused on Video / Image Processing and Multimedia Communications

PB - Institute of Electrical and Electronics Engineers Inc.

ER -