English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26450/27046 (98%)
Visitors : 12189582      Online Users : 494
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU 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
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ksu.edu.tw/handle/987654321/29283

    Title: 走道上多重障礙物之偵測
    其他題名: Detection of Multiple Barrier on Sidewalk
    Authors: 李信葳
    Li, Sin-Wei
    Contributors: 吳明芳;謝聰烈
    Wu, Ming-Fang;Hsieh, Tsung-Lieh
    ???metadata.dc.contributor.other???: 電機工程研究所
    Keywords: 背景消除法;走道;障礙物;影像處理
    Background elimination method;Sidewalk;Obstacles;Image processing
    Date: 2018
    Issue Date: 2018-11-13 11:11:40 (UTC+8)
    Abstract: 本論文主要是利用數位影像處理技術於走道上有多重障礙物的檢測,過程中將彩色影像轉成灰階影像,並配合背景消除法來取得前景的影像,為了使影像輪廓清楚,在影像處理部分使用Sobel、膨脹、侵蝕與中間值濾波等影像處理技術,並且搭配本論文設計出的演算法來區分開移動物體與靜止物體的顏色矩形框,將移動物體表示為藍色矩形框,靜止物體示為紅色矩形框,來呈現不同背景與多重障礙物體的區分,藉以偵測障礙物所在位置。本技術可用於搭配障礙物訊息之發送,以通知管理人員來清除障礙物,避免老年人與盲人或行動不便者被絆倒。 本論文最後以三個走道場景加以實作測試,結果顯示都可以順利辨識出走道上的移動物體與障礙物體,且成功率達97.4%~99.3%,顯示本論文所提方法的正確性及實用性。
    The purpose of this thesis is to apply the image processing technology in the detection of multiple obstacles in the sidewalk. During the process, the color images are converted into grayscale images and the background subtraction method is used to obtain the foreground image. In order to obtain the image outline of obstacles, the image processing techniques such as Sobel,expansion, erosion, median filtering and their algorithm are designed in this thesis to distinguish the color rectangular box from the moving objects and stationary objects. The moving objects are represented as the blue rectangle and the stationary objects are shown as a red rectangular box, to distinguish the difference between multiple objects, and to detect the location of obstacles. This technology can sent the obstruction information to notify managers to clear obstacles and prevent the elderly, the blind or people with disabilities from tripping over. This thesis is put into practice in three sidewalk. The results show that both the moving object and the obstacle in the walkway can be successfully identified, and the success rate is between 97.4% and 99.3%. It shows the correctness and practicability of the proposed method .
    Appears in Collections:[電機工程系所] 博碩士論文

    Files in This Item:

    File Description SizeFormat
    106KSUT0442015.pdf2875KbAdobe PDF63View/Open

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

    ©Kun Shan University Library and Information Center
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback