Image segmentation for human tracking using sequential-image-based hierarchical adaptation

Akira Utsumi, Jun Ohya

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

10 Citations (Scopus)

Abstract

We propose a novel method of extracting a moving object region from each frame in a series of images regardless of complex, changing background using statistical knowledge about the target. In vision systems for 'real worlds' like a human motion tracker, a priori knowledge about the target and environment is often limited (e.g., only the approximate size of the target is known) and is insufficient for extracting the target motion directly. In our approach, information about both target object and environment is extracted with a small amount of given knowledge about the target object. Pixel value (color, intensity, etc.) distributions for both the target object and background region are adaptively estimated from the input image sequence based on the knowledge. Then, the probability of each pixel being associated with the target object is calculated. The target motion can be extracted from the calculated stochastic image. We confirmed the stability of this approach through experiments.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages911-916
Number of pages6
DOIs
Publication statusPublished - 1998
Externally publishedYes
EventProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Santa Barbara, CA, USA
Duration: 1998 Jun 231998 Jun 25

Other

OtherProceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CitySanta Barbara, CA, USA
Period98/6/2398/6/25

Fingerprint

Image segmentation
Pixels
Color
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering

Cite this

Utsumi, A., & Ohya, J. (1998). Image segmentation for human tracking using sequential-image-based hierarchical adaptation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 911-916) https://doi.org/10.1109/CVPR.1998.698713

Image segmentation for human tracking using sequential-image-based hierarchical adaptation. / Utsumi, Akira; Ohya, Jun.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. p. 911-916.

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

Utsumi, A & Ohya, J 1998, Image segmentation for human tracking using sequential-image-based hierarchical adaptation. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 911-916, Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, 98/6/23. https://doi.org/10.1109/CVPR.1998.698713
Utsumi A, Ohya J. Image segmentation for human tracking using sequential-image-based hierarchical adaptation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. p. 911-916 https://doi.org/10.1109/CVPR.1998.698713
Utsumi, Akira ; Ohya, Jun. / Image segmentation for human tracking using sequential-image-based hierarchical adaptation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1998. pp. 911-916
@inproceedings{e99911442919467c9a0f52da5bd16987,
title = "Image segmentation for human tracking using sequential-image-based hierarchical adaptation",
abstract = "We propose a novel method of extracting a moving object region from each frame in a series of images regardless of complex, changing background using statistical knowledge about the target. In vision systems for 'real worlds' like a human motion tracker, a priori knowledge about the target and environment is often limited (e.g., only the approximate size of the target is known) and is insufficient for extracting the target motion directly. In our approach, information about both target object and environment is extracted with a small amount of given knowledge about the target object. Pixel value (color, intensity, etc.) distributions for both the target object and background region are adaptively estimated from the input image sequence based on the knowledge. Then, the probability of each pixel being associated with the target object is calculated. The target motion can be extracted from the calculated stochastic image. We confirmed the stability of this approach through experiments.",
author = "Akira Utsumi and Jun Ohya",
year = "1998",
doi = "10.1109/CVPR.1998.698713",
language = "English",
isbn = "0818684976",
pages = "911--916",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Image segmentation for human tracking using sequential-image-based hierarchical adaptation

AU - Utsumi, Akira

AU - Ohya, Jun

PY - 1998

Y1 - 1998

N2 - We propose a novel method of extracting a moving object region from each frame in a series of images regardless of complex, changing background using statistical knowledge about the target. In vision systems for 'real worlds' like a human motion tracker, a priori knowledge about the target and environment is often limited (e.g., only the approximate size of the target is known) and is insufficient for extracting the target motion directly. In our approach, information about both target object and environment is extracted with a small amount of given knowledge about the target object. Pixel value (color, intensity, etc.) distributions for both the target object and background region are adaptively estimated from the input image sequence based on the knowledge. Then, the probability of each pixel being associated with the target object is calculated. The target motion can be extracted from the calculated stochastic image. We confirmed the stability of this approach through experiments.

AB - We propose a novel method of extracting a moving object region from each frame in a series of images regardless of complex, changing background using statistical knowledge about the target. In vision systems for 'real worlds' like a human motion tracker, a priori knowledge about the target and environment is often limited (e.g., only the approximate size of the target is known) and is insufficient for extracting the target motion directly. In our approach, information about both target object and environment is extracted with a small amount of given knowledge about the target object. Pixel value (color, intensity, etc.) distributions for both the target object and background region are adaptively estimated from the input image sequence based on the knowledge. Then, the probability of each pixel being associated with the target object is calculated. The target motion can be extracted from the calculated stochastic image. We confirmed the stability of this approach through experiments.

UR - http://www.scopus.com/inward/record.url?scp=0032319549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032319549&partnerID=8YFLogxK

U2 - 10.1109/CVPR.1998.698713

DO - 10.1109/CVPR.1998.698713

M3 - Conference contribution

SN - 0818684976

SP - 911

EP - 916

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -