English  |  正體中文  |  简体中文  |  Items with full text/Total items : 90069/105176 (86%)
Visitors : 6521294      Online Users : 545
RC Version 6.0 © 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://asiair.asia.edu.tw/ir/handle/310904400/111239

    Title: 融入群體智能的擴增實境互動系統
    Authors: 黃韋鑫
    Contributors: 行動商務與多媒體應用學系
    Keywords: Kinect體感裝置、群體智能、擴增實境、Kinect sensor、Swarm Intelligence、Augmented Reality
    Date: 2018
    Issue Date: 2018-07-30 13:37:10 (UTC+8)
    Publisher: 亞洲大學
    Abstract: 由於科技的進步,近年來擴增實境逐漸被重視,應用在很多不同領域上。隨著Pokemon GO結合GPS的擴增實境遊戲和IKEA家具佈置功能應用的擴增實境App被廣為的使用,成功吸引了更多公司投入擴增實境開發。但是傳統的擴增實境都只是單純將虛擬的物件加諸於實際場景中,使用者僅能觀看效果而無法與目標物進行互動。此外,傳統擴增實境只能藉由偵測特製的簡單標記(Marker)來呈現虛擬物件,無法直接從攝影機視窗中任意選取區域當成標記來進行辨識,增加製作上的繁複手續,而混合實境則需佩戴設備,價格昂貴。
    Due to the advancement of science and technology, Augmented Reality (AR) has been attracted more attention in recent years and applied in many different fields. With the game applications of Pokemon GO combined with GPS and IKEA’s App with furniture layout functions, AR has been widely used and successfully attracted more companies to invest in application development. However, traditional AR is simply to add virtual objects to the actual scene. Users can only watch the result and cannot interact with the target. In addition, the traditional AR can only display virtual objects by detecting specially-made simple markers. It can't be used by selecting an arbitrary region in the camera window as a marker to identify the target, and makes the detection procedures complicated. For Mixed Reality (MR) technology, it is not
    convenient to wear equipment and the price is also high.
    This study builds an interactive system that expands reality so that users can use physical gestures to direct objects in the virtual scene to experience the immersion in the virtual world. The system is designed and developed using a Unity3D game engine and a seabed scene as the virtual environment. The KinectV2 sensor is used to capture human skeleton information and then Microsoft’s SDK is applied to videos for background removal and gesture recognition. A set of gestures is also defined to manipulate a school of fish. Fish behavior is simulated through swarm intelligence,
    allowing fish swimming patterns to be presented in a very natural way.
    Appears in Collections:[行動商務與多媒體應用學系] 博碩士論文

    Files in This Item:

    File Description SizeFormat

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

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback