English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27320/39164
Visitors : 2474240      Online Users : 38
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/987654321/18431

Title: 基於即時影像之智慧型自走車避障與動態追蹤控制
Intelligent Mobile Robot Obstacle Avoidance and Dynamic Tracking Control Based on Real-Time Image
Authors: Jia-Jun Zhan
詹嘉峻
Contributors: NTOU:Department of Communications Navigation and Control Engineering
國立臺灣海洋大學:通訊與導航工程系
Keywords: 自走車;避障;動態追蹤;影像
Intelligent Mobile Robot;Obstacle Avoidance;Dynamic Tracking;Image
Date: 2010
Issue Date: 2011-07-04
Abstract: 本篇論文研究目的分為障礙物避障與動態追蹤控制兩部份,動態追蹤部分是以CCD攝影機捕捉到的影像作為輸入,再分別使用線性轉換與模糊理論設計系統的控制器,實現自走車的即時動態物體辨識與追蹤,並且比較其差異性。目標影像辨識過程是經由面積與色彩篩選並算出與自走車的距離,以及目標物在影像二維座標上的位置。此系統主要利用模糊方向控制器及模糊速度控制器分別控制自走車左右兩輪的速度,使得自走車能夠穩定、快速的與目標物維持固定的安全距離。障礙物避障部分是藉由CCD攝影機捕捉到影像,用影像處理擷取出障礙物邊緣且算出與自走車的距離,再與超音波感測到的距離做比較,以距離較短的作為輸入,此目的是為了防止自走車面臨到封閉空間及CCD視覺影像失去功用所設置的。並且使用室內定位系統來提供自走車的座標位置,使自走車可以成功到達我們所設定的終點。本研究使用LabView8.5來撰寫人機介面、C語言撰寫影像處理以及WiFi(802.11b)無線網路作為自走車與電腦之間的數值傳遞,結合以上所敘來控制自走車。實驗證明,本論文所設計的智慧型控制器運行良好。
The purpose of this thesis is to design intelligent control scheme for obstacle avoidance and dynamic tracking of a wheeled mobile robot (WMR). A CCD camera captures the images of obstacles and dynamic object. Through color screening and area calculation, the image process procedure is able to estimate the distance between the object and the WMR and the position of the object in the image coordinate. The controller is designed by linear transformation and fuzzy theory. The proposed control scheme utilizes a fuzzy steering controller and a fuzzy speed controller to control the speed of right and left wheels. This allows the WMR to follow a dynamic object as well as to maintain a fixed safety distance stably and quickly. The WMR achieves dynamic object recognition and tracking in real-time. Comparison is also provided. In the case of obstacle avoidance, objects are captured via image processing which calculates the distance between the obstacle and the WMR. The ultrasonic sensors also detect the distance at the same time. The shorter distance is then used as the input of the controller. This will prevent the WMR from facing closed space and the CCD losing the visual function. The use of a localization system is to provide the position of the WMR, which can make the WMR reach the destination successfully. We use LabView8.5 to write human-machine interface. Image processing is coded by C language. WiFi (802.11b) wireless network is utilized to transmit of command signals between the WMR and the computer. The experiments show that the proposed control scheme works well.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M97670017
http://ntour.ntou.edu.tw/ir/handle/987654321/18431
Appears in Collections:[通訊與導航工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML249View/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