Fast scene change detection using direct feature extraction from MPEG compressed videos

Young Min Kim, Sung Woo Choi, Seong Whan Lee

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

1 Citation (Scopus)

Abstract

In order to process video data efficiently, a video segmentation technique through scene change detection must be employed. Many of advanced video applications require manipulations of compressed video signals. So, the scene change detection process is achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. In this paper, we propose a fast scene change detection algorithm using direct feature extraction from MPEG compressed videos, and evaluate this technique using sample video data. This process was made possible by a new mathematical formulation for deriving the edge information directly from the DCT coefficients.

Original languageEnglish
Title of host publicationProceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3
Subtitle of host publicationImage, Speech, and Signal Processing
EditorsM. Vanrell, J. J. Villanueva, A. Sanfeliu, R. Alquezar, T. Huang, J. Serra
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages174-177
Number of pages4
Volume3
ISBN (Electronic)0769507506
DOIs
Publication statusPublished - 2000 Jan 1
Event15th International Conference on Pattern Recognition, ICPR 2000 - Barcelona, Spain
Duration: 2000 Sep 32000 Sep 7

Other

Other15th International Conference on Pattern Recognition, ICPR 2000
CountrySpain
CityBarcelona
Period00/9/300/9/7

Fingerprint

Feature extraction
Pixels

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Kim, Y. M., Choi, S. W., & Lee, S. W. (2000). Fast scene change detection using direct feature extraction from MPEG compressed videos. In M. Vanrell, J. J. Villanueva, A. Sanfeliu, R. Alquezar, T. Huang, & J. Serra (Eds.), Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3: Image, Speech, and Signal Processing (Vol. 3, pp. 174-177). [903513] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2000.903513

Fast scene change detection using direct feature extraction from MPEG compressed videos. / Kim, Young Min; Choi, Sung Woo; Lee, Seong Whan.

Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3: Image, Speech, and Signal Processing. ed. / M. Vanrell; J. J. Villanueva; A. Sanfeliu; R. Alquezar; T. Huang; J. Serra. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2000. p. 174-177 903513.

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

Kim, YM, Choi, SW & Lee, SW 2000, Fast scene change detection using direct feature extraction from MPEG compressed videos. in M Vanrell, JJ Villanueva, A Sanfeliu, R Alquezar, T Huang & J Serra (eds), Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3: Image, Speech, and Signal Processing. vol. 3, 903513, Institute of Electrical and Electronics Engineers Inc., pp. 174-177, 15th International Conference on Pattern Recognition, ICPR 2000, Barcelona, Spain, 00/9/3. https://doi.org/10.1109/ICPR.2000.903513
Kim YM, Choi SW, Lee SW. Fast scene change detection using direct feature extraction from MPEG compressed videos. In Vanrell M, Villanueva JJ, Sanfeliu A, Alquezar R, Huang T, Serra J, editors, Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3: Image, Speech, and Signal Processing. Vol. 3. Institute of Electrical and Electronics Engineers Inc. 2000. p. 174-177. 903513 https://doi.org/10.1109/ICPR.2000.903513
Kim, Young Min ; Choi, Sung Woo ; Lee, Seong Whan. / Fast scene change detection using direct feature extraction from MPEG compressed videos. Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3: Image, Speech, and Signal Processing. editor / M. Vanrell ; J. J. Villanueva ; A. Sanfeliu ; R. Alquezar ; T. Huang ; J. Serra. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2000. pp. 174-177
@inproceedings{876fb097ea0242e48fd36a4af8119da4,
title = "Fast scene change detection using direct feature extraction from MPEG compressed videos",
abstract = "In order to process video data efficiently, a video segmentation technique through scene change detection must be employed. Many of advanced video applications require manipulations of compressed video signals. So, the scene change detection process is achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. In this paper, we propose a fast scene change detection algorithm using direct feature extraction from MPEG compressed videos, and evaluate this technique using sample video data. This process was made possible by a new mathematical formulation for deriving the edge information directly from the DCT coefficients.",
author = "Kim, {Young Min} and Choi, {Sung Woo} and Lee, {Seong Whan}",
year = "2000",
month = "1",
day = "1",
doi = "10.1109/ICPR.2000.903513",
language = "English",
volume = "3",
pages = "174--177",
editor = "M. Vanrell and Villanueva, {J. J.} and A. Sanfeliu and R. Alquezar and T. Huang and J. Serra",
booktitle = "Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fast scene change detection using direct feature extraction from MPEG compressed videos

AU - Kim, Young Min

AU - Choi, Sung Woo

AU - Lee, Seong Whan

PY - 2000/1/1

Y1 - 2000/1/1

N2 - In order to process video data efficiently, a video segmentation technique through scene change detection must be employed. Many of advanced video applications require manipulations of compressed video signals. So, the scene change detection process is achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. In this paper, we propose a fast scene change detection algorithm using direct feature extraction from MPEG compressed videos, and evaluate this technique using sample video data. This process was made possible by a new mathematical formulation for deriving the edge information directly from the DCT coefficients.

AB - In order to process video data efficiently, a video segmentation technique through scene change detection must be employed. Many of advanced video applications require manipulations of compressed video signals. So, the scene change detection process is achieved by analyzing the video directly in the compressed domain, thereby avoiding the overhead of decompressing video into individual frames in the pixel domain. In this paper, we propose a fast scene change detection algorithm using direct feature extraction from MPEG compressed videos, and evaluate this technique using sample video data. This process was made possible by a new mathematical formulation for deriving the edge information directly from the DCT coefficients.

UR - http://www.scopus.com/inward/record.url?scp=85058518313&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058518313&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2000.903513

DO - 10.1109/ICPR.2000.903513

M3 - Conference contribution

AN - SCOPUS:85058518313

VL - 3

SP - 174

EP - 177

BT - Proceedings - 15th International Conference on Pattern Recognition, ICPR 2000 - Volume 3

A2 - Vanrell, M.

A2 - Villanueva, J. J.

A2 - Sanfeliu, A.

A2 - Alquezar, R.

A2 - Huang, T.

A2 - Serra, J.

PB - Institute of Electrical and Electronics Engineers Inc.

ER -