English  |  正體中文  |  简体中文  |  Items with full text/Total items : 75982/75982 (100%)
Visitors : 28170076      Online Users : 181
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/987654321/8677

    Title: 以搜尋為基礎的道路線及障礙物偵測;Search-based Lane and Obstacle Detection
    Authors: 劉士誠;Shi-Chen Liu
    Contributors: 資訊工程研究所
    Keywords: 搜尋;道路線;障礙物;偵測;lane;obstacle;detection;search
    Date: 2003-06-25
    Issue Date: 2009-09-22 11:32:49 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 日益繁忙的社會,交通運輸事業越顯複雜,人們對於交通安全的需求也越來越重視。電腦視覺及影像處理技術的研究也越來越成熟,已被廣泛考慮運用在自動駕駛、輔助駕駛、車輛監控…等交通運輸的議題上。本論文的研究即是發展用於輔助安全駕駛上,以搜尋為基礎 (search-based) 的道路線及障礙物偵測的方法。 本論文的主要研究在於如何快速並有效地偵測出道路影像中的道路線以及前車所在的位置。傳統偵測道路線段的方法,通常是針對影像中的單一像素點 (pixel) 或是單一掃瞄線 (scan line) 來進行決策與判斷;不同於舊式的線段偵測方法,我們嘗試將像素點之間的關連性建立起來,建立道路模型 (road model) 配合像素強度 (pixel intensity) 或邊界強度的累積量加以搜尋,來達到偵測道路線的目的。其中,我們利用四種不同的分析方式 (原始影像、二值化處理、第一像素差、第二像素差) 來獲得不同的影像強度,並比較其效果。本論文所提出的方法,能夠有效的克服由於天候變化以及其他車輛對影像所造成的影響。 在實驗方面,我們對於六種類型的影像: 晴天、陰天、黃昏、下雨、白色車輛、及其他車輛跨越道路線,加以分析,均能正確並有效率的偵測出道路線及前車。 People pay their attention on the safe driving day after day. The computer vision and image processing techniques are broad applied on the safe driving, for example: automatic driving system, vehicle flow rate motoring, etc. In this thesis, we propose a search-based method for lane and obstacle detection. Our goal is to detect the lane markings and obstacles in the road images efficiently. Conventional detection methods analyze pixels one by one under the assumption in which the processes of any two pixels are independent. Unlike conventional methods, we try to construct the relationship among pixels to detect lane markings and obstacles during detection. We here use four kinds of information: original images, bi-level thresholded images, the first difference maps, and the second difference maps for analysis. In the experiments, six kinds of images: sunny, cloudy, dusky, rainy, white-car influence, and car on the lanemarking images are used to evaluate the performance of the proposed system.
    Appears in Collections:[資訊工程研究所] 博碩士論文

    Files in This Item:

    File SizeFormat

    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 ©   - 隱私權政策聲明