English  |  正體中文  |  简体中文  |  Items with full text/Total items : 65231/98744 (66%)
Visitors : 31949734      Online Users : 3685
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/987654321/111153


    Title: 根據物件空間關係變化之影片相似尋取 : 考慮隱含關係
    Other Titles: Similarity retrieval of videos based on the movement of the object : considering implied relationship
    Authors: 蘇珩;Su, Heng
    Contributors: 淡江大學資訊管理學系碩士班
    梁恩輝
    Keywords: 影片尋取;空間關係;相似尋取;Video Retrieval;spatial relationship;Similarity Retrieval
    Date: 2016
    Issue Date: 2017-08-24 23:45:19 (UTC+8)
    Abstract: 近年來影片資料量隨著資訊科技進步設備的普及越發增長快速,而進行影片尋取的方法有許多種,使用基於內容的相似尋取是個較適宜的方法之ㄧ。
    在影片中,相鄰影格間內因物件移動而產生的空間關係變化是尋取的一個重要資訊,因此本文以影片中兩兩物件的空間關係與其變化為基礎並考慮「隱含關係」來進行影片間是否相似之評量,達到影片相似尋取之目的。最後,我們以範例說明利用我們提出的方法可以根據影格之間物件的空間關係變化作為查詢條件之影片相似尋取。
    Recently, the quantity of video information has increased at a high speed due to the improvement of the information technology. There are many methods for video retrieval. Similarity retrieval based on the contents is one of the suitable methods.
    In the video, the change of the spatial relationship between objects due to the movement of the object provides important information. In this paper, the spatial relationship between objects and its change are used as a base for determining if two videos are similar. In the mean time, the “implied relationship” is also considered in this paper for similarity retrieval of video. Finally, an example is given to demonstrate the process of the proposed method.
    Appears in Collections:[資訊管理學系暨研究所] 學位論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML223View/Open

    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