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

Seong Whan Lee, Young Min Kim, Sung Woo Choi

Research output: Contribution to journalArticle

117 Citations (Scopus)

Abstract

In order to process video data efficiently, a video segmentation technique through scene change detection must be required. This is a fundamental operation used in many digital video applications such as digital libraries, video on demand (VOD), etc. Many of these 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. First, we derive binary edge maps from the AC coefficients in blocks which were discrete cosine transformed. Second, we measure edge orientation, strength and offset using correlation between the AC coefficients in the derived binary edge maps. Finally, we match two consecutive frames using these two features (edge orientation and strength). This process was made possible by a new mathematical formulation for deriving the edge information directly from the discrete cosine transform (DCT) coefficients. We have shown that the proposed algorithm is faster or more accurate than the previously known scene change detection algorithms.

Original languageEnglish
Pages (from-to)240-254
Number of pages15
JournalIEEE Transactions on Multimedia
Volume2
Issue number4
DOIs
Publication statusPublished - 2000 Dec 1

Fingerprint

Feature extraction
Video on demand
Digital libraries
Discrete cosine transforms
Pixels

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

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

In: IEEE Transactions on Multimedia, Vol. 2, No. 4, 01.12.2000, p. 240-254.

Research output: Contribution to journalArticle

@article{6ae0e882dfa14276840bfbf5879b2ebd,
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 required. This is a fundamental operation used in many digital video applications such as digital libraries, video on demand (VOD), etc. Many of these 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. First, we derive binary edge maps from the AC coefficients in blocks which were discrete cosine transformed. Second, we measure edge orientation, strength and offset using correlation between the AC coefficients in the derived binary edge maps. Finally, we match two consecutive frames using these two features (edge orientation and strength). This process was made possible by a new mathematical formulation for deriving the edge information directly from the discrete cosine transform (DCT) coefficients. We have shown that the proposed algorithm is faster or more accurate than the previously known scene change detection algorithms.",
author = "Lee, {Seong Whan} and Kim, {Young Min} and Choi, {Sung Woo}",
year = "2000",
month = "12",
day = "1",
doi = "10.1109/6046.890059",
language = "English",
volume = "2",
pages = "240--254",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

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

AU - Lee, Seong Whan

AU - Kim, Young Min

AU - Choi, Sung Woo

PY - 2000/12/1

Y1 - 2000/12/1

N2 - In order to process video data efficiently, a video segmentation technique through scene change detection must be required. This is a fundamental operation used in many digital video applications such as digital libraries, video on demand (VOD), etc. Many of these 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. First, we derive binary edge maps from the AC coefficients in blocks which were discrete cosine transformed. Second, we measure edge orientation, strength and offset using correlation between the AC coefficients in the derived binary edge maps. Finally, we match two consecutive frames using these two features (edge orientation and strength). This process was made possible by a new mathematical formulation for deriving the edge information directly from the discrete cosine transform (DCT) coefficients. We have shown that the proposed algorithm is faster or more accurate than the previously known scene change detection algorithms.

AB - In order to process video data efficiently, a video segmentation technique through scene change detection must be required. This is a fundamental operation used in many digital video applications such as digital libraries, video on demand (VOD), etc. Many of these 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. First, we derive binary edge maps from the AC coefficients in blocks which were discrete cosine transformed. Second, we measure edge orientation, strength and offset using correlation between the AC coefficients in the derived binary edge maps. Finally, we match two consecutive frames using these two features (edge orientation and strength). This process was made possible by a new mathematical formulation for deriving the edge information directly from the discrete cosine transform (DCT) coefficients. We have shown that the proposed algorithm is faster or more accurate than the previously known scene change detection algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0034481494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034481494&partnerID=8YFLogxK

U2 - 10.1109/6046.890059

DO - 10.1109/6046.890059

M3 - Article

AN - SCOPUS:0034481494

VL - 2

SP - 240

EP - 254

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 4

ER -