An automatic algorithm for semantic object generation and temporal tracking

Jianping Fan, Ahmed Elmagarmid

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Automatic semantic video object extraction is an important step for providing content-based video coding, indexing and retrieval. However, it is very difficult to design a generic semantic video object extraction technique, which can provide variant semantic video objects by using the same function. Since the presence and absence of persons in an image sequence provide important clues about video content, automatic face detection and human being generation are very attractive for content-based video database applications. For this reason, we propose a novel face detection and semantic human object generation algorithm. The homogeneous image regions with accurate boundaries are first obtained by integrating the results of color edge detection and region growing procedures. The human faces are detected from these homogeneous image regions by using skin color segmentation and facial filters. These detected faces are then used as object seed for semantic human object generation. The correspondences of the detected faces and semantic human objects along time axis are further exploited by a contour-based temporal tracking procedure.

Original languageEnglish
Pages (from-to)145-164
Number of pages20
JournalSignal Processing: Image Communication
Volume17
Issue number2
DOIs
Publication statusPublished - 1 Feb 2002
Externally publishedYes

Fingerprint

Semantics
Face recognition
Color
Edge detection
Image coding
Seed
Skin

Keywords

  • Edge detection
  • Face detection
  • Human object generation
  • Key objects
  • Region growing
  • Tracking

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

An automatic algorithm for semantic object generation and temporal tracking. / Fan, Jianping; Elmagarmid, Ahmed.

In: Signal Processing: Image Communication, Vol. 17, No. 2, 01.02.2002, p. 145-164.

Research output: Contribution to journalArticle

@article{0e5d0b8e137c406182fabe0b568ebd0c,
title = "An automatic algorithm for semantic object generation and temporal tracking",
abstract = "Automatic semantic video object extraction is an important step for providing content-based video coding, indexing and retrieval. However, it is very difficult to design a generic semantic video object extraction technique, which can provide variant semantic video objects by using the same function. Since the presence and absence of persons in an image sequence provide important clues about video content, automatic face detection and human being generation are very attractive for content-based video database applications. For this reason, we propose a novel face detection and semantic human object generation algorithm. The homogeneous image regions with accurate boundaries are first obtained by integrating the results of color edge detection and region growing procedures. The human faces are detected from these homogeneous image regions by using skin color segmentation and facial filters. These detected faces are then used as object seed for semantic human object generation. The correspondences of the detected faces and semantic human objects along time axis are further exploited by a contour-based temporal tracking procedure.",
keywords = "Edge detection, Face detection, Human object generation, Key objects, Region growing, Tracking",
author = "Jianping Fan and Ahmed Elmagarmid",
year = "2002",
month = "2",
day = "1",
doi = "10.1016/S0923-5965(01)00012-1",
language = "English",
volume = "17",
pages = "145--164",
journal = "Signal Processing: Image Communication",
issn = "0923-5965",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - An automatic algorithm for semantic object generation and temporal tracking

AU - Fan, Jianping

AU - Elmagarmid, Ahmed

PY - 2002/2/1

Y1 - 2002/2/1

N2 - Automatic semantic video object extraction is an important step for providing content-based video coding, indexing and retrieval. However, it is very difficult to design a generic semantic video object extraction technique, which can provide variant semantic video objects by using the same function. Since the presence and absence of persons in an image sequence provide important clues about video content, automatic face detection and human being generation are very attractive for content-based video database applications. For this reason, we propose a novel face detection and semantic human object generation algorithm. The homogeneous image regions with accurate boundaries are first obtained by integrating the results of color edge detection and region growing procedures. The human faces are detected from these homogeneous image regions by using skin color segmentation and facial filters. These detected faces are then used as object seed for semantic human object generation. The correspondences of the detected faces and semantic human objects along time axis are further exploited by a contour-based temporal tracking procedure.

AB - Automatic semantic video object extraction is an important step for providing content-based video coding, indexing and retrieval. However, it is very difficult to design a generic semantic video object extraction technique, which can provide variant semantic video objects by using the same function. Since the presence and absence of persons in an image sequence provide important clues about video content, automatic face detection and human being generation are very attractive for content-based video database applications. For this reason, we propose a novel face detection and semantic human object generation algorithm. The homogeneous image regions with accurate boundaries are first obtained by integrating the results of color edge detection and region growing procedures. The human faces are detected from these homogeneous image regions by using skin color segmentation and facial filters. These detected faces are then used as object seed for semantic human object generation. The correspondences of the detected faces and semantic human objects along time axis are further exploited by a contour-based temporal tracking procedure.

KW - Edge detection

KW - Face detection

KW - Human object generation

KW - Key objects

KW - Region growing

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=0036466953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036466953&partnerID=8YFLogxK

U2 - 10.1016/S0923-5965(01)00012-1

DO - 10.1016/S0923-5965(01)00012-1

M3 - Article

AN - SCOPUS:0036466953

VL - 17

SP - 145

EP - 164

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

SN - 0923-5965

IS - 2

ER -