English  |  正體中文  |  简体中文  |  Items with full text/Total items : 65317/65317 (100%)
Visitors : 21373390      Online Users : 246
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.ncu.edu.tw/handle/987654321/2932


    Title: 即時眼部狀態偵測系統之研究;A Real-time Eye State Detection System
    Authors: 許尹融;Yin-Jung Hsu
    Contributors: 機械工程研究所
    Keywords: 即時影像處理;眨眼辨識;虹膜偵測;Real-time Image Processing;Blink Recognition;Iris Detection
    Date: 2008-06-18
    Issue Date: 2009-09-21 12:00:58 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 由於駕駛疲勞易導致車禍發生,所以當駕駛者處於低程度的專注力時,在車禍發生前給予警告是很重要的。根據研究結果顯示,當駕駛者的專注力低落時,眨眼的頻率就會逐漸地增加,例如駕駛疲勞。 本研究藉由USB介面的網路攝影機發展了一套即時且非接觸式的眼部狀態偵測系統,透過影像處理的方式,達到追蹤駕駛者的眼睛、辨識眨眼與偵測虹膜等目的。本系統將CCD網路攝影機所擷取的彩色影像作為系統輸入,經由灰階處理、二值化與連通域標記演算法、型態學等方法的處理,篩選出可能的眼睛區域,然後再進行樣板比對與眼部區域的特徵分析。完成這些處理之後,系統除了會建立一個即時搜尋區域,加快下一張影像的計算速度之外,還會同步地記錄駕駛者的眼睛狀態。這些紀錄將可進一步地用來計算眨眼次數,分析駕駛者的專注力程度,以期能於駕駛疲勞時,適時地警告駕駛者有危險。 經由實測的驗證結果,此系統在正常且均勻的室內光照條件下,其平均眨眼辨識率與虹膜偵測率分別可達88.64%及98.24%。 Driver fatigue leads to many traffic accidents. It’s important to warn the unconscious driver before the accident occurs. When the conscious level of driver becomes low, the frequency of blinks will increase. In this thesis, we develop a real-time eye state detection system. The system can track driver’s eye, recognize blinks and detect iris by image analysis. Color frames are grabbed by CCD webcam, and then they are analyzed to find eye candidates by gray scale transformation, binary converting, connected component labeling algorithm, morphology, etc. After completing the eye template matching and feature analyzing, the system can record driver’s eye state. These data can be utilized further to take count of blinks that we can analyze the conscious level of driver. In the indoor environment with normal and uniform illumination, the accuracy of blink recognition and iris detection are 88.64% and 98.24% respectively.
    Appears in Collections:[機械工程研究所] 博碩士論文

    Files in This Item:

    File SizeFormat
    0KbUnknown640View/Open


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

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明