Semiautomatic Segmentation Using Spatio-Temporal Gradual Region Merging for MPEG-4

Young Ro Kim, Jae Hwan Kim, Yoon Kim, Sung-Jea Ko

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The video coding standard MPEG-4 is enabling content-based functionalities. It takes advantage of a prior decomposition of sequences into video object planes (VOP's) so that each VOP represents a semantic object. Therefore, the extraction of semantic video objects is crucial initial part. In this paper, we present an efficient region based semi-automatic segmentation system, which combines low level automatic region segmentation with interactive method for defining and tracking high level semantic video objects. The proposed segmentation system extracts accurate object boundaries using gradual region merging and bi-directional temporal boundary refinement. The system comprises of two steps: an initial object extraction step where user input in the starting frame is used to extract a semantic object; and an object tracking step where underlying regions of the semantic object are tracked and grouped through successive frames. Experiments with different types of videos show the efficiency of the proposed system in semantic object extraction.

Original languageEnglish
Pages (from-to)2526-2534
Number of pages9
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE86-A
Issue number10
Publication statusPublished - 2003 Oct 1

Fingerprint

MPEG-4
Merging
Segmentation
Semantics
Motion Picture Experts Group standards
Image coding
Object
Region Segmentation
Interactive Methods
Decomposition
Object Tracking
Video Coding
Refinement
Decompose
Experiments

Keywords

  • Object tracking
  • Region merging
  • Segmentation
  • Semantic video object

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Information Systems

Cite this

Semiautomatic Segmentation Using Spatio-Temporal Gradual Region Merging for MPEG-4. / Kim, Young Ro; Kim, Jae Hwan; Kim, Yoon; Ko, Sung-Jea.

In: IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E86-A, No. 10, 01.10.2003, p. 2526-2534.

Research output: Contribution to journalArticle

@article{fb8531a786874b5a800441e98259b2f2,
title = "Semiautomatic Segmentation Using Spatio-Temporal Gradual Region Merging for MPEG-4",
abstract = "The video coding standard MPEG-4 is enabling content-based functionalities. It takes advantage of a prior decomposition of sequences into video object planes (VOP's) so that each VOP represents a semantic object. Therefore, the extraction of semantic video objects is crucial initial part. In this paper, we present an efficient region based semi-automatic segmentation system, which combines low level automatic region segmentation with interactive method for defining and tracking high level semantic video objects. The proposed segmentation system extracts accurate object boundaries using gradual region merging and bi-directional temporal boundary refinement. The system comprises of two steps: an initial object extraction step where user input in the starting frame is used to extract a semantic object; and an object tracking step where underlying regions of the semantic object are tracked and grouped through successive frames. Experiments with different types of videos show the efficiency of the proposed system in semantic object extraction.",
keywords = "Object tracking, Region merging, Segmentation, Semantic video object",
author = "Kim, {Young Ro} and Kim, {Jae Hwan} and Yoon Kim and Sung-Jea Ko",
year = "2003",
month = "10",
day = "1",
language = "English",
volume = "E86-A",
pages = "2526--2534",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Semiautomatic Segmentation Using Spatio-Temporal Gradual Region Merging for MPEG-4

AU - Kim, Young Ro

AU - Kim, Jae Hwan

AU - Kim, Yoon

AU - Ko, Sung-Jea

PY - 2003/10/1

Y1 - 2003/10/1

N2 - The video coding standard MPEG-4 is enabling content-based functionalities. It takes advantage of a prior decomposition of sequences into video object planes (VOP's) so that each VOP represents a semantic object. Therefore, the extraction of semantic video objects is crucial initial part. In this paper, we present an efficient region based semi-automatic segmentation system, which combines low level automatic region segmentation with interactive method for defining and tracking high level semantic video objects. The proposed segmentation system extracts accurate object boundaries using gradual region merging and bi-directional temporal boundary refinement. The system comprises of two steps: an initial object extraction step where user input in the starting frame is used to extract a semantic object; and an object tracking step where underlying regions of the semantic object are tracked and grouped through successive frames. Experiments with different types of videos show the efficiency of the proposed system in semantic object extraction.

AB - The video coding standard MPEG-4 is enabling content-based functionalities. It takes advantage of a prior decomposition of sequences into video object planes (VOP's) so that each VOP represents a semantic object. Therefore, the extraction of semantic video objects is crucial initial part. In this paper, we present an efficient region based semi-automatic segmentation system, which combines low level automatic region segmentation with interactive method for defining and tracking high level semantic video objects. The proposed segmentation system extracts accurate object boundaries using gradual region merging and bi-directional temporal boundary refinement. The system comprises of two steps: an initial object extraction step where user input in the starting frame is used to extract a semantic object; and an object tracking step where underlying regions of the semantic object are tracked and grouped through successive frames. Experiments with different types of videos show the efficiency of the proposed system in semantic object extraction.

KW - Object tracking

KW - Region merging

KW - Segmentation

KW - Semantic video object

UR - http://www.scopus.com/inward/record.url?scp=0242664701&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242664701&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0242664701

VL - E86-A

SP - 2526

EP - 2534

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 10

ER -