English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26269/26864 (98%)
Visitors : 10391172      Online Users : 55
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/987654321/26698

    Title: 一個即時交通速限辨識與警示系統
    其他題名: A Dynamic Real-time Recognition and Warning System for Traffic Speed Limit Signs
    Authors: 曾建瑋
    Tseng, Chien-Wei
    指導教授: 蔣元隆
    Yuan-Long Jeang
    Keywords: 速限辨識;即時影像處理;霍夫轉換
    Identification of speed limit;Real-time image processing;Hough transform
    Date: 2015
    Issue Date: 2017-02-16 11:13:12 (UTC+8)
    Abstract: 即時交通速限辨識對於駕駛很重要。靜態辨識易受到環境因素影響導致失敗。動態辨識,利用連續多張影像來進行辨識,可減少環境因素,但可能導致處理速度較慢。因此,本研究提出一種基於動態影像處理的辨識系統。系統先偵測是否有遇到速限標誌,一旦偵測到速限標誌,系統就鎖定該標誌,然後以較密集的時間間距來連續拍攝以確定其速限。系統先經過影像處理去除多餘的雜訊;然後,透過霍夫轉換與長寬比進行篩選,以達到避免雜訊干擾。然後我們使用Google所維護的Tesseract-OCR進行辨識。系統會將每幀影像經過辨識後,取重複率最高的作為辨識結果。系統目前在時速60~70公里間,天氣良好的條件下的識別率大約85%左右。雖不是很高,但做為行車輔助系統,其功能尚稱可行。
    The topic is very important. Static identification is vulnerable to environmental factors while dynamic identification can reduce it but with a slow speed. This study proposes a system based on dynamic image processing. The system first detect whether there is a speed limitation sign. Once the sign has been detected, the system will lock the sign and take a series of images. Then, the system performs image processing to avoid noise interference. Then the system uses Google Maintained Tesseract-OCR Identification System to recognize. Each image will be count the repetition rate and the highest one will be selected. The recognition rate is about 85% in average under the condition that when the car speed is about 60~70 kilometers and a good weather. Though the recognition rate is not so high, however, for the assistance of the drivers, the system is feasible enough.
    Appears in Collections:[資訊工程系所] 博碩士論文

    Files in This Item:

    File SizeFormat
    103KSUT0115001-001.pdf2917KbAdobe PDF203View/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