English  |  正體中文  |  简体中文  |  Items with full text/Total items : 6491/11663
Visitors : 24929749      Online Users : 46
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: http://ir.ncue.edu.tw/ir/handle/987654321/11735

Title: Applying both kinematic and attribute information for a target tracking algorithm
Authors: Chung, Yi-Nung;Chen, Joy
Contributors: 電機工程學系
Date: 1997-09
Issue Date: 2012-07-02T02:06:05Z
Publisher: Chinese Automatic Control Society
Abstract: A multi-sensor data fusion algorithm is developed in this paper, which combines a decentralized estimation approach together with image processing to obtain target attribute information. A neural network algorithm is applied to solve the problem of obtaining target attribute information. The major advantage of this fusion technique is that it uses data from several kinds of sensors to obtain better target measurement information and a more accurate estimation.
多目標追蹤(Multi-Target Tracking)系統中,若能結合多感測器偵測系統,則追蹤系統可同時採用多感測所得之資料,並截長補短以求取更精確的追蹤結果,吾人乃應用分散式濾波器原理,推導一資料融合運算程序,以協助雷達系統追蹤之工作。然一般研究的運算程序中僅考慮各感測器所接收之運動數量資料(Kinematic Quantity Information),如目標之位置,速度等。吾人認為若能同時考慮目標型態與形狀等,將可提高目標確認機率,以及降低軌道估計誤差,尤其是當目標物有交叉運動時。其中目標型能之確認,吾人將採用影像處理程序(Image Processing),及配合應用類神經網路(Neural Network)之處理方式,吾人相信此結合運動數量資料與目標特徵之多感測器資料融合運算程序,將可得到更精確的追蹤效果。
Relation: Journal of Control Systems and Technology, 5(3): 203-209
Appears in Collections:[電機工程學系] 期刊論文

Files in This Item:

File SizeFormat
2050200710001.pdf71KbAdobe PDF480View/Open

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