English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27248/39091
Visitors : 2414908      Online Users : 75
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/987654321/33615

Title: 路面紋理辨識應用於自走車導引之研究
Application of Texture Recognition on Autonomous Vehicle Guidance
Authors: 陳奕融
劉倫偉
Contributors: 國立臺灣海洋大學:機械與機電工程學系
Keywords: LBP演算法;GLCM演算法;投影轉換法;線性內插法;影像處理;紋理辨識;自走車
Date: 2012-06
Issue Date: 2013-04-24T06:21:48Z
Publisher: 2012中華民國系統科學與工程研討會 (2012 NSSSE)
Abstract: 本論文中設計一輛可辨識前方是否為可行走區域並沿著可行走之區域行進之智慧型自走車。自走車的導引系統,利用路面紋理辨識道路,使自走車在未知的環境下,取得前方路面紋理資訊作為導引自走車的依據。
導引系統使用置於自走車平台上的網路攝影機,擷取實驗場之影像,透過投影轉換法建構出實驗場正視圖,並利用線性內插法改善轉正後正視圖之影像品質,再以LBP演算法比對正視圖與資料庫之紋理,辨識出可行走之區域,判定前方路面狀況,執行相應之動作,達到自走車導引行進之功能。如果實驗場地面紋理為隨機型紋理,則再加入GLCM演算法輔助辨識道路。
In this thesis, an intelligent autonomous vehicle that can recognize the moveable road areas in front of it and move along these roads was proposed. The guidance system of the vehicle uses texture recognition to distinguish the road areas from the environment, which enables the system to utilize this texture information as a basis of guidance in an unknown environment.
The guidance system proposed uses a webcam placed on the vehicle to capture the images of the surrounding field. Next, the images are transformed to a top-down view of the field by a perspective transformation. Then, linear interpolation is employed to improve the image quality. Finally, the LBP algorithm is used to compare the field images with the textures in the database to identify the moveable road areas. Further more, if the texture of road surface is of a random nature, the GLCM algorithm is added to assist recognition. Once the conditions in front are determined, the guidance system will perform corresponding actions to achieve autonomous vehicle movements.
URI: http://ntour.ntou.edu.tw/handle/987654321/33615
Appears in Collections:[機械與機電工程學系] 演講及研討會

Files in This Item:

File Description SizeFormat
index.html0KbHTML389View/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