English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 56552/90363 (63%)
造訪人次 : 11820672      線上人數 : 133
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/987654321/114769


    題名: 使用BeagleBoard-xM完成機載影像處理之研究
    其他題名: A study on the onboard image processing using a BeagleBoard-xM
    作者: 陳昱良;Chen, Yu-Liang
    貢獻者: 淡江大學航空太空工程學系碩士班
    蕭富元;Hsiao, Fu-Yuen
    關鍵詞: Android;ARM+DSP;BeagleBoard-xM;OpenCV;Real-time image processin;安卓系統;即時影像處理
    日期: 2017
    上傳時間: 2018-08-03 15:03:27 (UTC+8)
    摘要: 本論文主要探討使用DSP 來進行機載影像處理的相關技術,並且透過
    BeagleBoard-xM 來具體落實此項研究。目前無人機上的影像導航功能,大多是將影像回傳至地面站,加以處理後,再以命令形式上傳至機載電腦。這種架構不僅會有傳輸時間延遲問題,也會造成影像資訊容易被雜訊影響。本論文探討利用DSP 直接在無人機上進行影像處理的相關技術,並使用BeagleBoard-xM 進行驗證。由於DSP 只有計算功能,進行機載影像導航還需要跟週邊設備如攝影機、天線等進行資料交換,所以需要一個CPU 與作業系統才能完成此項任務。本論文所選用的硬體BeagleBoard-xM 則採用ARM 搭配DSP,在此硬體架構上,本研究選用Android 作為作業系統,以及使用OpenCV 作為影像處理軟體。由於此架構尚未在Beagle Board 上實踐過,因此本論文主要貢獻在於將相關的軟、韌、硬體整合,並透過實驗驗證整合之後的系統運作狀況。本論文的研究成果,將來可以應用於無人機機載視訊導航。
    This thesis investigates the technology of navigating an unmanned aerial vehicle (UAV) with an onboard computer-vision navigation system computed on a DSP. The BeagleBoard-xM is selected as the hardware in this research. Currently, the computer-vision navigation is mostly realized by transmitting the image to the ground station, computing the command, and uploading to the onboard computer. This structure not only causes the delay of information, but also increases the noise of the image. This thesis studies the technology of performing image processing using an onboard DSP on a UAV, and implement
    the structure on the BeagleBoard-xM. Since a DSP only performs algorithm computation, a CPU along with a system software are is required to communicate with the peripherials, such as the camera and the attennas. In this thesis, we the BeagleBoard-xM as the hardware, which is equipped an ARM with a DSP. The Andoid is selected as the system software and OpenCV is selected as the platform to perform image processing. The integration of these hard-ware and softwares to implement them in the BeagleBoard-xM was not seen in the literature. As a result, our work offers the potential to apply DSP to the onboard computer-vision navigation of a UAV in the future.
    顯示於類別:[航空太空工程學系暨研究所] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML72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