English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27287/39131
Visitors : 2443380      Online Users : 40
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/18831

Title: 具視覺回授之人機互動系統設計與實現
Design and Implementation of a Human Machine Interactive System using Visual Feedback
Authors: Yen-Ju Tao
陶彥儒
Contributors: NTOU:Department of Electrical Engineering
國立臺灣海洋大學:電機工程學系
Keywords: 人機介面;互動裝置;視覺回授;影像處理;影像辨識;追蹤系統
Human-Machine Interface;Interactive Device;Visual Feedback;Image Processing;Image Recognition;Tracking System
Date: 2010
Issue Date: 2011-07-04T01:04:36Z
Abstract: 本論文主要利用電腦視覺及影像處理回授的方式來完成人機互動介面系統設計。在研究初期所設計的電子感測器定位系統和研究後期所設計的影像辨識系統,利用不同的定位辨識方式實現了人機互動介面系統。有別於一般常見的人機介面(如:滑鼠、鍵盤…等輸入介面),本論文所設計的人機互動介面系統包含了直覺化操作介面,且透過影像作為主要回授的方式,更可令使用者除了操作預設的顯示平面或電腦系統內部,系統以外的硬體也可透過此介面流暢的操作。 初期研究所設計的電子感測器定位系統,透過紅外線LED作為移動判斷的定位點,配合上紅外線攝影機擷取定位點之影像座標,利用視覺回授作影像處理、判斷分析後,再把欲控制的指令下達給滑鼠游標,來完成移動或選取及更多的功能;將系統裝上馬達,配合追蹤使用者系統,將可以增加使用者的自由度。 後期研究主要為設計不需使用電子裝置並也能達到同樣控制的效果,影像辨識互動系統利用手部作為主要定位點,配合攝影機擷取手部特徵影像,透過影像處理的程式撰寫,即可將手指的姿態和軌跡與相關的控制指令即時作連結,達到辨識、控制的效果,而在操作上也將更加直覺。
The purpose of this thesis is to use computer vision and visual feedback to accomplish a human machine interactive system. Two different approaches are used to implement this system. The first design is using electronic sensor localization system, and the second design is using image recognition system. Differing from general human machine interfaces, such as mouse, keyboard...etc., the interactive interface in the thesis involved more intuitive operation by using image feedback which lets user operate the system easier. First we design an electronic sensor localization system which uses infrared camera to capture the infrared LED as the localization point. After image processing, system can get the LED position information and control the screen cursor. Furthermore, adding motors to track users can improve the effective range. Next we wish user can operate the system without the extra electronic device. Therefore we choose fingers as the new localization points. After capturing the hand and finger feathers through a camera, user can control the system by hand intuitively.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M97530061
http://ntour.ntou.edu.tw/ir/handle/987654321/18831
Appears in Collections:[電機工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML153View/Open


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

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback