中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/68803
English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 80990/80990 (100%)
造訪人次 : 41679902      線上人數 : 1444
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU 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://ir.lib.ncu.edu.tw/handle/987654321/68803


    題名: 以Kinect為基礎之步態及姿態測量系統;A Kinect-based Gait and Posture Assessment System
    作者: 林晟弘;Lin,Sheng-Hung
    貢獻者: 資訊工程學系
    關鍵詞: 物理治療;評估表;關節活動度;姿態測量;步態測量;Kinect;Physical therapy;Evaluation form;Range of joint motion;Posture Assessment;Gait Assessment;Kinect
    日期: 2015-07-28
    上傳時間: 2015-09-23 14:30:18 (UTC+8)
    出版者: 國立中央大學
    摘要: 在台灣,當病患來到復健診所診治時,醫生或復健師都會對病患進行評估,目的是了解病患目前的狀況,進而訂定有效的治療計畫。大部分的復健專家通常採用一些步態和姿勢的評估表單,然後藉由視覺評估的方式,來判斷一個人是否具有良好的行走步態或站立姿勢。事實上,要能夠徹底並精確地執行步態和姿勢評估,需要許多專業上的知識和技巧。視覺評估的優點是簡單、不需要昂貴的設備,但同時它的缺點是不精確的、主觀的、和低效率等。因此,復健專家在每個病患的評估上,可能會遭遇到:在每次復健治療後無法得到客觀且一致性的評估結果之問題,導致復健專家無法制訂出良好的治療計劃來幫助患者從治療計劃中迅速復元並早日恢復正常的日常生活。
    因此,我們需要一個電腦化的步態和姿態評估系統來為病人進行客觀的輔助評估。一個好的電腦化評估系統應該要能夠提供整個量測過程的歷史紀錄和準確的測量結果,當然,較低成本的電腦化評估系統能夠讓一般診間更願意採用且易普及化,這促使我們開發以Kinect為基礎的步態和姿態評估系統。

    基於不同的評估需求,本論文提出兩套子系統,其中包含 (1)步態測量子系統 (2)姿態測量子系統以及 (3)關節活動度測量子系統。我們充分利用了微軟Kinect的感測平台其能夠提供全身骨架追蹤及低成本等優點。由於Kinect在骨架關節點的追蹤上仍然有些不準確的誤差,我們提出了一些特別的演算法來處理這些誤差,並提供在步態、姿態和關節活動度的測量上更精確的量測數據,我們也提出了一些實驗設計來驗證測試我們所設計的系統,系統的準確性的表現則是與傳統臨床上的手動量測作為比較。
    ;In Taiwan, when a patient is admitted at a rehabilitation clinic, he or she will be assessed by rehabilitation specialists to devise an appropriate treatment program. Most of the rehabilitation professionals usually adopt the visual assessment incorporated with some gait and posture charts to assess whether one has good gaits or postures while one is walking or standing still. In fact, the ability to perform a gait and posture evaluation accurately and thoroughly requires many skills on the part of rehabilitation professionals. While the advantages of the visual assessment are its simplicity and no need of expensive equipment, its disadvantages are imprecise, subjective, inefficient, etc. Therefore, rehabilitation specialists encounter the problem of being unable to objectively assess the treatment effect after each individual course of treatment. Owing to this problem, it is difficult for rehabilitation specialists to modify their treatment programs to help patients quickly recover from treatment programs and back to normal daily life.
    Therefore, a computerized gait and posture assessment system is needed. A good computerized gait and posture assessment system should be able to provide precise measurements about gaits and postures and output documents of the treatment and progress history. Of course, if the cost of the assessment system is low enough, then more rehabilitation clinics will be willing to adopt the system for their treatments. This motivated us to develop a Kinect-based gait and posture assessment system. The assessment system consists of three sub-systems: (1) the gait assessment sub-system, (2) the posture assessment sub-system and (3) the range of joint motion assessment sub-system. We fully utilize the advantages of the Microsoft Kinect which is a viable and low-cost sensing platform capable to provide full-body and limb tracking. Since the Kinect is still subject to inaccurate tracking and skeleton placement, some special algorithms have to be developed to provide precise measurements about gaits, postures, and range of motion for several critical joints. Several experiments are designed to test the proposed assessment system. The performance of the system is compared with manual measurements performed by rehabilitation specialists.
    顯示於類別:[資訊工程研究所] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML315檢視/開啟


    在NCUIR中所有的資料項目都受到原著作權保護.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明