Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain

Zhongqi Guo; Ru Lai; Luzheng Bi; Xiaochun Bu

Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain

Zhongqi Guo, Ru Lai^*, Luzheng Bi, Xiaochun Bu

^*Corresponding author for this work

School of Mechanical Engineering

Beijing Institute of Technology

Research output: Contribution to conference › Paper › peer-review

Abstract

For the uncalibrated visual servoing system, we present an online estimation method for image Jacobian matrix of robot. In order to improve robustness to noise, we choose the image moments as image features, and estimate the image Jacobian matrix based on Kalman filter. In order to solve the problem of slow convergence of visual error, we introduce an adaptive gain in the control law. We also set a threshold of the infinity norm of the visual error to decrease the camera velocity when visual error is very close to zero. Simulation results demonstrate the validity of our approach.

Original language	English
Publication status	Published - 2018
Event	8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018 - Tengzhou, Shandong, China Duration: 2 Nov 2018 → 6 Nov 2018

Conference

Conference	8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018
Country/Territory	China
City	Tengzhou, Shandong
Period	2/11/18 → 6/11/18

Keywords

Adaptive Gain
Image Jacobian Matrix
Image Moments
Kalman Filter

Cite this

Guo, Z., Lai, R., Bi, L., & Bu, X. (2018). Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

Guo, Zhongqi ; Lai, Ru ; Bi, Luzheng et al. / Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

@conference{975cd5013f9042f68853e8b9f9608513,

title = "Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain",

abstract = "For the uncalibrated visual servoing system, we present an online estimation method for image Jacobian matrix of robot. In order to improve robustness to noise, we choose the image moments as image features, and estimate the image Jacobian matrix based on Kalman filter. In order to solve the problem of slow convergence of visual error, we introduce an adaptive gain in the control law. We also set a threshold of the infinity norm of the visual error to decrease the camera velocity when visual error is very close to zero. Simulation results demonstrate the validity of our approach.",

keywords = "Adaptive Gain, Image Jacobian Matrix, Image Moments, Kalman Filter",

author = "Zhongqi Guo and Ru Lai and Luzheng Bi and Xiaochun Bu",

note = "Publisher Copyright: {\textcopyright} ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Application.; 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018 ; Conference date: 02-11-2018 Through 06-11-2018",

year = "2018",

language = "English",

}

Guo, Z, Lai, R, Bi, L & Bu, X 2018, 'Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain', Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China, 2/11/18 - 6/11/18.

Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain. / Guo, Zhongqi; Lai, Ru; Bi, Luzheng et al.
2018. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain

AU - Guo, Zhongqi

AU - Lai, Ru

AU - Bi, Luzheng

AU - Bu, Xiaochun

N1 - Publisher Copyright: © ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Application.

PY - 2018

Y1 - 2018

N2 - For the uncalibrated visual servoing system, we present an online estimation method for image Jacobian matrix of robot. In order to improve robustness to noise, we choose the image moments as image features, and estimate the image Jacobian matrix based on Kalman filter. In order to solve the problem of slow convergence of visual error, we introduce an adaptive gain in the control law. We also set a threshold of the infinity norm of the visual error to decrease the camera velocity when visual error is very close to zero. Simulation results demonstrate the validity of our approach.

AB - For the uncalibrated visual servoing system, we present an online estimation method for image Jacobian matrix of robot. In order to improve robustness to noise, we choose the image moments as image features, and estimate the image Jacobian matrix based on Kalman filter. In order to solve the problem of slow convergence of visual error, we introduce an adaptive gain in the control law. We also set a threshold of the infinity norm of the visual error to decrease the camera velocity when visual error is very close to zero. Simulation results demonstrate the validity of our approach.

KW - Adaptive Gain

KW - Image Jacobian Matrix

KW - Image Moments

KW - Kalman Filter

UR - http://www.scopus.com/inward/record.url?scp=85057986464&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85057986464

T2 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018

Y2 - 2 November 2018 through 6 November 2018

ER -

Guo Z, Lai R, Bi L, Bu X. Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain. 2018. Paper presented at 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and Control Applications, ISCIIA and ITCA 2018, Tengzhou, Shandong, China.

Online estimation for image Jacobian matrix based on Kalman filter with image moments and adaptive gain

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this