Constrained video object segmentation by color masks and MPEG-7 descriptors

Fatih Porikli, Yao Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present an automatic and computationally conservative boundary extraction method using available priori information in a framework consists of change detection mask, region growing, and trajectory motion. Instead of segmenting a entire video frame, only the regions belong to a target object specified by a set of rules are detected. One example of such rules is skin color features of a human body part. The processing domain is limited to the pixels that satisfy color or geometric rules. These rules are represented as a detection mask and implemented as a look-up table. As a result, significant computational reduction and real-time performance are achieved. The framework utilizes color consistency within a centroid-linkage growing technique to grow initial regions. Region seeds are selected among the pixels in the detection mask. The similarity thresholds are adapted from the MPEG-7 dominant color descriptors. The segmentation results of a frame diffused to the next frame and region statistics such as trajectory, percentage of the changed pixels, etc., are registered to determine the moving regions. A computational load comparison of the constrained region growing and regular region growing shows significant reduction in the complexity.

Original languageEnglish (US)
Title of host publicationProceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages441-444
Number of pages4
Volume1
ISBN (Print)0780373049
DOIs
StatePublished - 2002
Event2002 IEEE International Conference on Multimedia and Expo, ICME 2002 - Lausanne, Switzerland
Duration: Aug 26 2002Aug 29 2002

Other

Other2002 IEEE International Conference on Multimedia and Expo, ICME 2002
CountrySwitzerland
CityLausanne
Period8/26/028/29/02

Fingerprint

Masks
Color
Pixels
Trajectories
Seed
Skin
Statistics
Mask
MPEG-7
Segmentation
Processing

ASJC Scopus subject areas

  • Archaeology
  • Electrical and Electronic Engineering

Cite this

Porikli, F., & Wang, Y. (2002). Constrained video object segmentation by color masks and MPEG-7 descriptors. In Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002 (Vol. 1, pp. 441-444). [1035813] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICME.2002.1035813

Constrained video object segmentation by color masks and MPEG-7 descriptors. / Porikli, Fatih; Wang, Yao.

Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2002. p. 441-444 1035813.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Porikli, F & Wang, Y 2002, Constrained video object segmentation by color masks and MPEG-7 descriptors. in Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. vol. 1, 1035813, Institute of Electrical and Electronics Engineers Inc., pp. 441-444, 2002 IEEE International Conference on Multimedia and Expo, ICME 2002, Lausanne, Switzerland, 8/26/02. https://doi.org/10.1109/ICME.2002.1035813
Porikli F, Wang Y. Constrained video object segmentation by color masks and MPEG-7 descriptors. In Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 2002. p. 441-444. 1035813 https://doi.org/10.1109/ICME.2002.1035813
Porikli, Fatih ; Wang, Yao. / Constrained video object segmentation by color masks and MPEG-7 descriptors. Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2002. pp. 441-444
@inproceedings{6317f7e1a7c5441ba1908bbed3c68ffa,
title = "Constrained video object segmentation by color masks and MPEG-7 descriptors",
abstract = "We present an automatic and computationally conservative boundary extraction method using available priori information in a framework consists of change detection mask, region growing, and trajectory motion. Instead of segmenting a entire video frame, only the regions belong to a target object specified by a set of rules are detected. One example of such rules is skin color features of a human body part. The processing domain is limited to the pixels that satisfy color or geometric rules. These rules are represented as a detection mask and implemented as a look-up table. As a result, significant computational reduction and real-time performance are achieved. The framework utilizes color consistency within a centroid-linkage growing technique to grow initial regions. Region seeds are selected among the pixels in the detection mask. The similarity thresholds are adapted from the MPEG-7 dominant color descriptors. The segmentation results of a frame diffused to the next frame and region statistics such as trajectory, percentage of the changed pixels, etc., are registered to determine the moving regions. A computational load comparison of the constrained region growing and regular region growing shows significant reduction in the complexity.",
author = "Fatih Porikli and Yao Wang",
year = "2002",
doi = "10.1109/ICME.2002.1035813",
language = "English (US)",
isbn = "0780373049",
volume = "1",
pages = "441--444",
booktitle = "Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Constrained video object segmentation by color masks and MPEG-7 descriptors

AU - Porikli, Fatih

AU - Wang, Yao

PY - 2002

Y1 - 2002

N2 - We present an automatic and computationally conservative boundary extraction method using available priori information in a framework consists of change detection mask, region growing, and trajectory motion. Instead of segmenting a entire video frame, only the regions belong to a target object specified by a set of rules are detected. One example of such rules is skin color features of a human body part. The processing domain is limited to the pixels that satisfy color or geometric rules. These rules are represented as a detection mask and implemented as a look-up table. As a result, significant computational reduction and real-time performance are achieved. The framework utilizes color consistency within a centroid-linkage growing technique to grow initial regions. Region seeds are selected among the pixels in the detection mask. The similarity thresholds are adapted from the MPEG-7 dominant color descriptors. The segmentation results of a frame diffused to the next frame and region statistics such as trajectory, percentage of the changed pixels, etc., are registered to determine the moving regions. A computational load comparison of the constrained region growing and regular region growing shows significant reduction in the complexity.

AB - We present an automatic and computationally conservative boundary extraction method using available priori information in a framework consists of change detection mask, region growing, and trajectory motion. Instead of segmenting a entire video frame, only the regions belong to a target object specified by a set of rules are detected. One example of such rules is skin color features of a human body part. The processing domain is limited to the pixels that satisfy color or geometric rules. These rules are represented as a detection mask and implemented as a look-up table. As a result, significant computational reduction and real-time performance are achieved. The framework utilizes color consistency within a centroid-linkage growing technique to grow initial regions. Region seeds are selected among the pixels in the detection mask. The similarity thresholds are adapted from the MPEG-7 dominant color descriptors. The segmentation results of a frame diffused to the next frame and region statistics such as trajectory, percentage of the changed pixels, etc., are registered to determine the moving regions. A computational load comparison of the constrained region growing and regular region growing shows significant reduction in the complexity.

UR - http://www.scopus.com/inward/record.url?scp=45749118695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45749118695&partnerID=8YFLogxK

U2 - 10.1109/ICME.2002.1035813

DO - 10.1109/ICME.2002.1035813

M3 - Conference contribution

SN - 0780373049

VL - 1

SP - 441

EP - 444

BT - Proceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002

PB - Institute of Electrical and Electronics Engineers Inc.

ER -