淡江大學機構典藏:Item 987654321/52427
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62805/95882 (66%)
Visitors : 3930359      Online Users : 766
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
    •  Adv. Search
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/52427


    Title: 以機器視覺為基礎之智慧型自動停車系統研究
    Other Titles: Research in vision-based intelligent automatic parking system
    Authors: 蘇育平;Su, Yu-ping
    Contributors: 淡江大學機械與機電工程學系碩士班
    孫崇訓;Sun, Chung-hsun
    Keywords: 影像處理;最小平方法;模糊控制器;階層式模糊控制器;Image Processing;Least Square Method;fuzzy controller;Hierarchical Fuzzy Controller
    Date: 2009
    Issue Date: 2010-09-23 17:40:07 (UTC+8)
    Abstract: 近年來，智慧型車輛控制的功能研發逐漸受到重視，其中智慧型自動停車的功能就是一個重要的研發方向之ㄧ。本研究將對自走車設計一個智慧性自動路邊停車系統。藉由自走車上之無線攝影機進行影像擷取。影像資訊的偵測是以影像處理演算法(Image Processing Algorithm)計算而得，其中車身角度是以最小平方法(Least Square Method)進行計算。獲得的資訊將在模糊控制器(Fuzzy Controller)中使用。自走車在前進控制過程中，將使自走車與車道線保持平行前進。如此自走車就能夠偵測停車格的前後方邊線作為偵測停車格的依據。在偵測到停車格後，將會執行自動停車程序。模糊控制器中我們考慮了三個輸入變數，導致模糊規則的數量龐大。因此，利用了階層式模糊控制器(Hierarchical Fuzzy Controller)來達到降低模糊規則數及運算量的目的。實驗結果顯示，我們所設計的自動停車系統在環境簡單的情況下，是能夠完成路邊停車的任務，也證明了其可行性與穩定性。
    Recently, The function of intelligent vehicle control is researched and pay attention to. The automatic parallel parking is one of important function. In this thesis, we design an intelligent automatic parallel parking system for mobile robot. Image capture is by wireless camera on the robot. The image Information detection between mobile robot and lane line is calculated by image processing algorithm. Moreover, the angle between robot and horizontal is calculated by least square method. The Information will be used in fuzzy controller. In the course of move forward control, the robot will keep parallel with lane line. Then, the mobile robot can detect the front and rear sidelines of the parking space. After parking space detecting, the mobile robot will execute the automatic parking process. In fuzzy control system, we consider three input variables, and it leads to large fuzzy rules. Thus, we utilize hierarchical fuzzy controller to reduce number of the fuzzy rules and computing requirement. Experimental results show the effectiveness of the proposed automatic parking system, when the environmental complexity is low.
    Appears in Collections:[Graduate Institute & Department of Mechanical and Electro-Mechanical Engineering] Thesis

    Files in This Item:

    File SizeFormat
    index.html0KbHTML314View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.

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