English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 49983/85139 (59%)
造訪人次 : 7793871      線上人數 : 33
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/87748


    題名: 一個根據空間事件進行影片尋取之基因演算法
    其他題名: A genetic algorithm for video retrieval based on spatial events
    作者: 林詒慧;Lin, Yi-Hui
    貢獻者: 淡江大學資訊管理學系碩士班
    梁恩輝;Liang,En-Hui
    關鍵詞: 影片尋取;相似尋取;基因演算法;影片相似度;Video Retrieval;Similarity Retreval;Genetic Algorithm;Video Similarity
    日期: 2013
    上傳時間: 2013-04-13 11:39:46 (UTC+8)
    摘要: 隨著影片資料量越來越龐大,如何在大量的資料中,進行影片尋取,儼然成為一個重要的議題。而基於內容的影片相似尋取(Content-based Video Retrieval)是一種處理影片資料較合適的解決方法之一。
    本論文中,我們基於影片中物件的空間關係,利用基因演算法來進行影片尋取。針對物件間的空間變化關係定義了六種空間事件,並將其以字串表示,稱為空間事件字串。參考影片與查詢影片皆可產生出其影片之空間事件字串序列。接著,基於空間事件字串序列利用基因演算法與適應函數中的四種指標,查詢出參考影片中與查詢影片最為相似之影片片段。最後,實驗結果顯示本方法可成功地將與查詢影片相似之多組皆找尋出來。
    When the video data becomes more and more, how to perform video retrieval in the large amount data is an important issue. Content-based video retrieval is one of the appropriate solutions for retrieving video data.
    In this thesis, a Genetic Algorithm is used for video retrieval based on the change of the spatial relationship between objects in the video.Six spatial events are defined for the change of spatial relationship between objects and represented as spatial event strings.A spatial event string sequence (SESS) is constructed for the reference video.A SESS is also constructed for the query video.Then, Searching for the video segment in the reference video similar to the query video based on their spatial event string sequences is performed using a Genetic Algorithm with four indicators for its fitness function. Finally, experiments are performed and the results show that multiple similar video segments to the query video can be located successfully.
    顯示於類別:[資訊管理學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML181檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋