English  |  正體中文  |  简体中文  |  Items with full text/Total items : 72271/72271 (100%)
Visitors : 23074036      Online Users : 611
RC Version 7.0 © 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://ir.lib.ncu.edu.tw/handle/987654321/68803

    Title: 以Kinect為基礎之步態及姿態測量系統;A Kinect-based Gait and Posture Assessment System
    Authors: 林晟弘;Lin,Sheng-Hung
    Contributors: 資訊工程學系
    Keywords: 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
    Date: 2015-07-28
    Issue Date: 2015-09-23 14:30:18 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 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。

    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.
    Appears in Collections:[資訊工程研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

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

    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 ©   - Feedback  - 隱私權政策聲明