Optical flow based model for scene cut detection

O. Fatemi, S. Zhang, Sethuraman Panchanathan

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Cut detection is a fundamental operation for video sequence segmentation. This paper presents an optical flow based model with linear prediction to realize cut detection in various transition conditions. Each frame of a video sequence is divided into 4×4 non-overlapping blocks. This model initiates the cut detection by backward block searching for match. Three continuous frames with the same matched block and the fourth predicted frame are grouped as a subsequence. The linearly predicted non-overlapping block locations in the fourth frame are defined as cut detectable region. The forward search for a match is performed between the third and fourth frames in the cut delectable region. Mismatched blocks indicate a scene change in these block locations, namely, a cut. This algorithm has a better performance for detecting cuts in quick scene changes, static scenes, and scenes with slow motion compared to techniques reported in the literature.

Original languageEnglish (US)
Pages (from-to)470-473
Number of pages4
JournalUnknown Journal
Volume1
StatePublished - 1996
Externally publishedYes

Fingerprint

Optical flows
Linear Models

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Optical flow based model for scene cut detection. / Fatemi, O.; Zhang, S.; Panchanathan, Sethuraman.

In: Unknown Journal, Vol. 1, 1996, p. 470-473.

Research output: Contribution to journalArticle

Fatemi, O. ; Zhang, S. ; Panchanathan, Sethuraman. / Optical flow based model for scene cut detection. In: Unknown Journal. 1996 ; Vol. 1. pp. 470-473.
@article{9130401b5fa840abaedce155923962a7,
title = "Optical flow based model for scene cut detection",
abstract = "Cut detection is a fundamental operation for video sequence segmentation. This paper presents an optical flow based model with linear prediction to realize cut detection in various transition conditions. Each frame of a video sequence is divided into 4×4 non-overlapping blocks. This model initiates the cut detection by backward block searching for match. Three continuous frames with the same matched block and the fourth predicted frame are grouped as a subsequence. The linearly predicted non-overlapping block locations in the fourth frame are defined as cut detectable region. The forward search for a match is performed between the third and fourth frames in the cut delectable region. Mismatched blocks indicate a scene change in these block locations, namely, a cut. This algorithm has a better performance for detecting cuts in quick scene changes, static scenes, and scenes with slow motion compared to techniques reported in the literature.",
author = "O. Fatemi and S. Zhang and Sethuraman Panchanathan",
year = "1996",
language = "English (US)",
volume = "1",
pages = "470--473",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",

}

TY - JOUR

T1 - Optical flow based model for scene cut detection

AU - Fatemi, O.

AU - Zhang, S.

AU - Panchanathan, Sethuraman

PY - 1996

Y1 - 1996

N2 - Cut detection is a fundamental operation for video sequence segmentation. This paper presents an optical flow based model with linear prediction to realize cut detection in various transition conditions. Each frame of a video sequence is divided into 4×4 non-overlapping blocks. This model initiates the cut detection by backward block searching for match. Three continuous frames with the same matched block and the fourth predicted frame are grouped as a subsequence. The linearly predicted non-overlapping block locations in the fourth frame are defined as cut detectable region. The forward search for a match is performed between the third and fourth frames in the cut delectable region. Mismatched blocks indicate a scene change in these block locations, namely, a cut. This algorithm has a better performance for detecting cuts in quick scene changes, static scenes, and scenes with slow motion compared to techniques reported in the literature.

AB - Cut detection is a fundamental operation for video sequence segmentation. This paper presents an optical flow based model with linear prediction to realize cut detection in various transition conditions. Each frame of a video sequence is divided into 4×4 non-overlapping blocks. This model initiates the cut detection by backward block searching for match. Three continuous frames with the same matched block and the fourth predicted frame are grouped as a subsequence. The linearly predicted non-overlapping block locations in the fourth frame are defined as cut detectable region. The forward search for a match is performed between the third and fourth frames in the cut delectable region. Mismatched blocks indicate a scene change in these block locations, namely, a cut. This algorithm has a better performance for detecting cuts in quick scene changes, static scenes, and scenes with slow motion compared to techniques reported in the literature.

UR - http://www.scopus.com/inward/record.url?scp=0029722772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029722772&partnerID=8YFLogxK

M3 - Article

VL - 1

SP - 470

EP - 473

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

ER -