Human tracking and silhouette extraction for human-robot interaction systems

Jung Ho Ahn, Cheolmin Choi, Sooyeong Kwak, Kilcheon Kim, Hyeran Byun

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this study, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with a pan-tilt stereo camera, so that it can assist in gesture and gait recognition in the field of Human-Robot Interaction (HRI). The proposed system consists of three modules: detection, tracking and silhouette extraction. These modules are robust to camera movements, and they work interactively in near real-time. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift-based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap was estimated in advance and then effectively incorporated into the graph-cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data, and it was shown to detect and track multiple people very well and also produce high-quality silhouettes.

Original languageEnglish
Pages (from-to)167-177
Number of pages11
JournalPattern Analysis and Applications
Volume12
Issue number2
DOIs
Publication statusPublished - 2009 Jun 1

Fingerprint

Human robot interaction
Cameras
Motion compensation
Computer vision
Color

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Ahn, Jung Ho ; Choi, Cheolmin ; Kwak, Sooyeong ; Kim, Kilcheon ; Byun, Hyeran. / Human tracking and silhouette extraction for human-robot interaction systems. In: Pattern Analysis and Applications. 2009 ; Vol. 12, No. 2. pp. 167-177.
@article{165400b95cd246fd8157b9a2c0cf4646,
title = "Human tracking and silhouette extraction for human-robot interaction systems",
abstract = "In this study, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with a pan-tilt stereo camera, so that it can assist in gesture and gait recognition in the field of Human-Robot Interaction (HRI). The proposed system consists of three modules: detection, tracking and silhouette extraction. These modules are robust to camera movements, and they work interactively in near real-time. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift-based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap was estimated in advance and then effectively incorporated into the graph-cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data, and it was shown to detect and track multiple people very well and also produce high-quality silhouettes.",
author = "Ahn, {Jung Ho} and Cheolmin Choi and Sooyeong Kwak and Kilcheon Kim and Hyeran Byun",
year = "2009",
month = "6",
day = "1",
doi = "10.1007/s10044-008-0112-3",
language = "English",
volume = "12",
pages = "167--177",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer London",
number = "2",

}

Human tracking and silhouette extraction for human-robot interaction systems. / Ahn, Jung Ho; Choi, Cheolmin; Kwak, Sooyeong; Kim, Kilcheon; Byun, Hyeran.

In: Pattern Analysis and Applications, Vol. 12, No. 2, 01.06.2009, p. 167-177.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Human tracking and silhouette extraction for human-robot interaction systems

AU - Ahn, Jung Ho

AU - Choi, Cheolmin

AU - Kwak, Sooyeong

AU - Kim, Kilcheon

AU - Byun, Hyeran

PY - 2009/6/1

Y1 - 2009/6/1

N2 - In this study, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with a pan-tilt stereo camera, so that it can assist in gesture and gait recognition in the field of Human-Robot Interaction (HRI). The proposed system consists of three modules: detection, tracking and silhouette extraction. These modules are robust to camera movements, and they work interactively in near real-time. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift-based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap was estimated in advance and then effectively incorporated into the graph-cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data, and it was shown to detect and track multiple people very well and also produce high-quality silhouettes.

AB - In this study, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with a pan-tilt stereo camera, so that it can assist in gesture and gait recognition in the field of Human-Robot Interaction (HRI). The proposed system consists of three modules: detection, tracking and silhouette extraction. These modules are robust to camera movements, and they work interactively in near real-time. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift-based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap was estimated in advance and then effectively incorporated into the graph-cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data, and it was shown to detect and track multiple people very well and also produce high-quality silhouettes.

UR - http://www.scopus.com/inward/record.url?scp=60949113707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60949113707&partnerID=8YFLogxK

U2 - 10.1007/s10044-008-0112-3

DO - 10.1007/s10044-008-0112-3

M3 - Article

AN - SCOPUS:60949113707

VL - 12

SP - 167

EP - 177

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 2

ER -