Presentation 1994/6/28
Construction of extended Kalman filter using neural networks;An application to the image processing
Hiroshi Kinjo, Tetsuhiko Yamamoto, Shiro Tamaki, Sigeru Omatu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new method of constructing the extended Kalman filter using the neural network which was used the system identification of the nonlinear system.The extended Kalman filter which are approximately linearized filter for the nonlinear system. First,neural network identify the nonlinear system.Second,after training the network and finished the system identification,the extended Kalman filter is constructed using the network.The extended Kalman filter with neural network is applied to the image processing.Simulation results show that the new system has good performance of the system idenfication and filtering for the image signals.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural networks / nonlinear system identification / state estimation / extended Kolman filter / image processing
Paper # NC94-17
Date of Issue

Conference Information
Committee NC
Conference Date 1994/6/28(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Construction of extended Kalman filter using neural networks;An application to the image processing
Sub Title (in English)
Keyword(1) neural networks
Keyword(2) nonlinear system identification
Keyword(3) state estimation
Keyword(4) extended Kolman filter
Keyword(5) image processing
1st Author's Name Hiroshi Kinjo
1st Author's Affiliation Department of Mechanical Systems Engineering,Faculty of Engineering,University of the Ryukyus()
2nd Author's Name Tetsuhiko Yamamoto
2nd Author's Affiliation Department of Mechanical Systems Engineering,Faculty of Engineering,University of the Ryukyus
3rd Author's Name Shiro Tamaki
3rd Author's Affiliation Department of Mechanical Systems Engineering,Faculty of Engineering,University of the Ryukyus
4th Author's Name Sigeru Omatu
4th Author's Affiliation Department of Information Science and Systems Engineering,Faculty of Engineering,University of Tokushima
Date 1994/6/28
Paper # NC94-17
Volume (vol) vol.94
Number (no) 129
Page pp.pp.-
#Pages 7
Date of Issue