National Changhua University of Education Institutional Repository : Item 987654321/11834
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 6507/11669
Visitors : 29917909      Online Users : 396
RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item:

Title: 應用類神經網路及擴展型多模預估器於多目標變速度追蹤
Authors: 黃羽賢;蘇進東;劉婉君;鍾翼能
Contributors: 電機工程學系
Keywords: 變速度檢測;資料結合;擴展型多模預估器;競爭性類神經網路
Maneuvering target detector;Data association;Extended multiple-model estimator;Competitive Hopfield neural network.
Date: 2011-04
Issue Date: 2012-07-02T02:11:28Z
Publisher: 朝陽科技大學
Abstract: 在雷達追蹤系統中,如何有效的掌握目標運動狀態是非常重要的, 其中以變速度 (Maneuvering) 檢測以及資料結合(Data
Multiple-model Estimator)來做一個多目標的變速度追蹤,資料結合技術應用競爭性類神經網路,運用此架構將可有效的改善追蹤的精確度及可靠性,當目標發生變速度時,加入擴展型多模預估器之系統,將可減少追蹤誤差,應用此架構將可同時解決目標變速度及資料結合的問題。
An approach of tracking multiple maneuvering targets using neural network algorithm and an adaptive procedure denoted extended multiple-model estimator is proposed in this project. With the developed algorithm, the system will improve the tracking accuracy and reliability of radar
surveillance. Target maneuvering situations are usually existed in radar tracking systems and the maneuvering will cause severe tracking errors. Therefore accurately detecting and estimating maneuvering status of targets is one essential step in the reduction of tracking errors. In this research, an equivalent filter bank structure is designed to estimate the status of target maneuvering situations. In order to achieve the optimal
correlation between measurements and the existing targets, a data association technique denoted competitive Hopfield neural network
is applied in this system. Base on this approach, we can solve the maneuvering and data association problems simultaneously
Relation: 2011資訊科技國際研討會, 朝陽科技大學, 2011年4月22日-23日
Appears in Collections:[Department and Graduate Institute of Electronic Engineering] Proceedings

Files in This Item:

File SizeFormat

All items in NCUEIR are protected by copyright, with all rights reserved.


DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback