Robot motion tracking system with multiple views

Hiroshi Yamano, Hideo Saito

研究成果: Conference contribution

抄録

In such a space where human workers and industrial robots work together, it has become necessary to monitor a robot motion for the safety. For such robot surveillance, we propose a robot tracking system from multiple view images. In this system, we treat tracking robot movement problem as an estimation problem of each pose parameter through all frames. This tracking algorithm consists of four stages, image generating stage, estimation stage, parameter searching stage, and prediction stage. At the first stage, robot area of real image is extracted by background subtraction. Here, Yuv color system is used because of reducing the change of lighting condition. By calibrating extrinsic and intrinsic parameters of all cameras with Tsai's method, we can project 3D model of the robot onto each camera. In the next stage, correlation of the input image and projected model image is calculated, which is defined by the area of robots in real and 3D images. At third stage, the pose parameters of the robot are estimated by maximizing the correlation. For computational efficiency, a high dimensional pose parameter space is divided into many low dimensional sub-spaces in accordance with the predicted pose parameters in the previous flame. We apply the proposed system for pose estimation of 5-axis robot manipulator. The estimated pose parameters are successfully matched with the actual pose of the robots.

元の言語English
ホスト出版物のタイトルProceedings of SPIE - The International Society for Optical Engineering
編集者D.P. Casasent, E L Hall
ページ329-338
ページ数10
4572
DOI
出版物ステータスPublished - 2001
イベントIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision - Boston, MA, United States
継続期間: 2001 10 292001 10 31

Other

OtherIntelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision
United States
Boston, MA
期間01/10/2901/10/31

Fingerprint

robot dynamics
robots
Robots
Cameras
cameras
Industrial robots
calibrating
surveillance
Computational efficiency
subtraction
illuminating
Manipulators
manipulators
flames
safety
Lighting

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

これを引用

Yamano, H., & Saito, H. (2001). Robot motion tracking system with multiple views. : D. P. Casasent, & E. L. Hall (版), Proceedings of SPIE - The International Society for Optical Engineering (巻 4572, pp. 329-338) https://doi.org/10.1117/12.444199

Robot motion tracking system with multiple views. / Yamano, Hiroshi; Saito, Hideo.

Proceedings of SPIE - The International Society for Optical Engineering. 版 / D.P. Casasent; E L Hall. 巻 4572 2001. p. 329-338.

研究成果: Conference contribution

Yamano, H & Saito, H 2001, Robot motion tracking system with multiple views. : DP Casasent & EL Hall (版), Proceedings of SPIE - The International Society for Optical Engineering. 巻. 4572, pp. 329-338, Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, Boston, MA, United States, 01/10/29. https://doi.org/10.1117/12.444199
Yamano H, Saito H. Robot motion tracking system with multiple views. : Casasent DP, Hall EL, 編集者, Proceedings of SPIE - The International Society for Optical Engineering. 巻 4572. 2001. p. 329-338 https://doi.org/10.1117/12.444199
Yamano, Hiroshi ; Saito, Hideo. / Robot motion tracking system with multiple views. Proceedings of SPIE - The International Society for Optical Engineering. 編集者 / D.P. Casasent ; E L Hall. 巻 4572 2001. pp. 329-338
@inproceedings{abb195c0cccb4f058dea53bf2917c985,
title = "Robot motion tracking system with multiple views",
abstract = "In such a space where human workers and industrial robots work together, it has become necessary to monitor a robot motion for the safety. For such robot surveillance, we propose a robot tracking system from multiple view images. In this system, we treat tracking robot movement problem as an estimation problem of each pose parameter through all frames. This tracking algorithm consists of four stages, image generating stage, estimation stage, parameter searching stage, and prediction stage. At the first stage, robot area of real image is extracted by background subtraction. Here, Yuv color system is used because of reducing the change of lighting condition. By calibrating extrinsic and intrinsic parameters of all cameras with Tsai's method, we can project 3D model of the robot onto each camera. In the next stage, correlation of the input image and projected model image is calculated, which is defined by the area of robots in real and 3D images. At third stage, the pose parameters of the robot are estimated by maximizing the correlation. For computational efficiency, a high dimensional pose parameter space is divided into many low dimensional sub-spaces in accordance with the predicted pose parameters in the previous flame. We apply the proposed system for pose estimation of 5-axis robot manipulator. The estimated pose parameters are successfully matched with the actual pose of the robots.",
keywords = "Industrial robot, Model matching, Motion analysis, Multiple views",
author = "Hiroshi Yamano and Hideo Saito",
year = "2001",
doi = "10.1117/12.444199",
language = "English",
volume = "4572",
pages = "329--338",
editor = "D.P. Casasent and Hall, {E L}",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Robot motion tracking system with multiple views

AU - Yamano, Hiroshi

AU - Saito, Hideo

PY - 2001

Y1 - 2001

N2 - In such a space where human workers and industrial robots work together, it has become necessary to monitor a robot motion for the safety. For such robot surveillance, we propose a robot tracking system from multiple view images. In this system, we treat tracking robot movement problem as an estimation problem of each pose parameter through all frames. This tracking algorithm consists of four stages, image generating stage, estimation stage, parameter searching stage, and prediction stage. At the first stage, robot area of real image is extracted by background subtraction. Here, Yuv color system is used because of reducing the change of lighting condition. By calibrating extrinsic and intrinsic parameters of all cameras with Tsai's method, we can project 3D model of the robot onto each camera. In the next stage, correlation of the input image and projected model image is calculated, which is defined by the area of robots in real and 3D images. At third stage, the pose parameters of the robot are estimated by maximizing the correlation. For computational efficiency, a high dimensional pose parameter space is divided into many low dimensional sub-spaces in accordance with the predicted pose parameters in the previous flame. We apply the proposed system for pose estimation of 5-axis robot manipulator. The estimated pose parameters are successfully matched with the actual pose of the robots.

AB - In such a space where human workers and industrial robots work together, it has become necessary to monitor a robot motion for the safety. For such robot surveillance, we propose a robot tracking system from multiple view images. In this system, we treat tracking robot movement problem as an estimation problem of each pose parameter through all frames. This tracking algorithm consists of four stages, image generating stage, estimation stage, parameter searching stage, and prediction stage. At the first stage, robot area of real image is extracted by background subtraction. Here, Yuv color system is used because of reducing the change of lighting condition. By calibrating extrinsic and intrinsic parameters of all cameras with Tsai's method, we can project 3D model of the robot onto each camera. In the next stage, correlation of the input image and projected model image is calculated, which is defined by the area of robots in real and 3D images. At third stage, the pose parameters of the robot are estimated by maximizing the correlation. For computational efficiency, a high dimensional pose parameter space is divided into many low dimensional sub-spaces in accordance with the predicted pose parameters in the previous flame. We apply the proposed system for pose estimation of 5-axis robot manipulator. The estimated pose parameters are successfully matched with the actual pose of the robots.

KW - Industrial robot

KW - Model matching

KW - Motion analysis

KW - Multiple views

UR - http://www.scopus.com/inward/record.url?scp=0035773925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035773925&partnerID=8YFLogxK

U2 - 10.1117/12.444199

DO - 10.1117/12.444199

M3 - Conference contribution

AN - SCOPUS:0035773925

VL - 4572

SP - 329

EP - 338

BT - Proceedings of SPIE - The International Society for Optical Engineering

A2 - Casasent, D.P.

A2 - Hall, E L

ER -