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 proceedingChapter

3 Citations (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 - International Conference on Pattern Recognition
Pages174-177
Number of pages4
Volume15
Edition3
Publication statusPublished - 2000

Fingerprint

Feature extraction
Pixels

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

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 Proceedings - International Conference on Pattern Recognition (3 ed., Vol. 15, pp. 174-177)

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

Proceedings - International Conference on Pattern Recognition. Vol. 15 3. ed. 2000. p. 174-177.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kim, YM, Choi, SW & Lee, SW 2000, Fast scene change detection using direct feature extraction from MPEG compressed videos. in Proceedings - International Conference on Pattern Recognition. 3 edn, vol. 15, pp. 174-177.
Kim YM, Choi SW, Lee SW. Fast scene change detection using direct feature extraction from MPEG compressed videos. In Proceedings - International Conference on Pattern Recognition. 3 ed. Vol. 15. 2000. p. 174-177
Kim, Young Min ; Choi, Sung Woo ; Lee, Seong Whan. / Fast scene change detection using direct feature extraction from MPEG compressed videos. Proceedings - International Conference on Pattern Recognition. Vol. 15 3. ed. 2000. pp. 174-177
@inbook{b3a7ad0a07c04b5ba8943d81aad2037b,
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",
language = "English",
volume = "15",
pages = "174--177",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "3",

}

TY - CHAP

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

Y1 - 2000

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=33750903343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750903343&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:33750903343

VL - 15

SP - 174

EP - 177

BT - Proceedings - International Conference on Pattern Recognition

ER -