English  |  正體中文  |  简体中文  |  Items with full text/Total items : 60696/93562 (65%)
Visitors : 1038922      Online Users : 31
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
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/74626

    Title: 移動機器人之火源偵測及追蹤系統設計
    Other Titles: The design of a fire detection and tracking system for a mobile robot
    Authors: 李後德;Lee, Hou-Te
    Contributors: 淡江大學機械與機電工程學系碩士班
    楊智旭;Yang, Jr-Syu
    Keywords: 火焰偵測;火焰追蹤;機器視覺;感測器;火災警報;防災;Fire Detection;Fire Tracking;Machine vision;sensor;Fire Alarm;Disaster Prevention
    Date: 2011
    Issue Date: 2011-12-28 19:06:12 (UTC+8)
    Abstract: 本研究主要目的為智慧型機器人之火焰偵測及追蹤系統設計,在火災發生的初期,透過機器視覺與智慧型控制技術,達到即時火源偵測並進行追蹤與警報發送任務,以掌握消防救災之最佳時期,降低人員傷亡與財產損失。
    本系統之移動平台為兩輪式自走車(Segway Rmp50),視覺監視系統以網路攝影機(Webcam)擷取即時影像,利用影像處理技術將影像空間型別轉換,再將RGB色彩空間轉換為YCbCr色彩空間,利用各色彩空間特性取得最佳參數,並以Y、Cb、Cr特性最佳化處理後,再進行二值化將火焰區塊具體顯示,使用座標平均法判斷火焰中心設計火焰辨識系統,最後結合模糊控制器完成火焰追蹤系統,達到火焰即時追蹤及初步警報發送功能。智慧型消防機器人可透過視覺系統得知環境資訊,判定火災事件,再由智慧型控制技術進行火源辨識,當感測器判斷為火災時,立即執行追蹤動作及發送警報,完成迅速確實的追蹤通報任務,達成消防通報目的。
    The objective of this thesis is to develop the fire detection and tracking system for an intelligent robot. Through the technology of machine vision and intelligent control, this intelligent robot can achieve the purpose of real-time fire detection, tracking and alarm transmission when the fire breaks out at the early stage in order to grasp the best opportunities for the fire rescue and to reduce the casualties and property losses.
    The mobile robot platform is a two-wheel self-propelled vehicle(Segway Rmp50). By using the webcam, the visual surveillance system captures the real-time image, and to convert the RGB color space to YCbCr color space by image processing technology. The optimal parameters of Y, Cb and Cr is obtained by using the color space characteristics. Then, the captured image is processed again by the binary technology. The fire recognition subsystem is designed by the center of fire feature. Finally, the real-time fire tracking and alarm system is developed by integrating the fire recognition subsystem and the fuzzy controller. The intelligent fire fighting robot can be applied to detect the fire event and get the environmental information by the machine vision subsystem. It is capable to make the fire tracking and send out fire alarm signal whenever the fire accident is detected.
    Appears in Collections:[機械與機電工程學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat

    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