淡江大學機構典藏:Item 987654321/114769
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62805/95882 (66%)
Visitors : 3985373      Online Users : 305
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
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/114769


    Title: 使用BeagleBoard-xM完成機載影像處理之研究
    Other Titles: A study on the onboard image processing using a BeagleBoard-xM
    Authors: 陳昱良;Chen, Yu-Liang
    Contributors: 淡江大學航空太空工程學系碩士班
    蕭富元;Hsiao, Fu-Yuen
    Keywords: Android;ARM+DSP;BeagleBoard-xM;OpenCV;Real-time image processin;安卓系統;即時影像處理
    Date: 2017
    Issue Date: 2018-08-03 15:03:27 (UTC+8)
    Abstract: 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.
    Appears in Collections:[Graduate Institute & Department of Aerospace Engineering] Thesis

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML240View/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