瑜珈姿態辨識-使用多重KINECT; Multiple Kinects Motion Sensing for Yoga

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/61570

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/61570

題名:	瑜珈姿態辨識-使用多重KINECT;Multiple Kinects Motion Sensing for Yoga
作者:	穆罕德;Ardiansyah,Mohammad Firdaus
貢獻者:	資訊工程學系
關鍵詞:	Kinect;Multiple;Human;Yoga;body;tracking;Multiple;Kinect
日期:	2013-08-16
上傳時間:	2013-10-08 15:22:35 (UTC+8)
出版者:	國立中央大學
摘要:	ABSTRACT Human motion tracking is receiving increasing attention from researchers of different fields of study nowadays. The interest is motivated by a wide range of applications, such as wireless healthcare, surveillance, and human-computer interaction. A complete model of human consists of both the movements and the shape of the human body skeleton. There are so many ways to track human motion, from marker sensing, marker less, optical, etc. Kinect sensor developed by Microsoft had done human tracking in 3d perspective and widely used in both in commercial and experiments purpose. However this Kinect method tracking by estimating depth image yield good result for simple gestures. In this study a novel approach is proposed to track complicated movement such as yoga movement with three Kinects in order to overcome kinect’s limitation. 摘要人體動作偵測最近在不同領域的研究中正逐漸變成一個令人關注的議題。無線健康照護、監控系統、人機互動等應用為促成此篇論文的動機。一個完整的人體模型包含動作以及骨架的形狀。有許多方法可以用來追蹤人體動作，配戴感測器、光學追蹤等。微軟開發的kinect可以在三維空間中完成人體姿態辨識，而且在商業、實驗用途都被廣泛地使用。然而kinect藉由估計深度圖像來追蹤的方法只對簡單的姿勢才能有較好的結果。本論文提出了一個新的方法，利用三部kinect克服單部kinect的限制，使其可以追蹤如瑜珈般複雜的動作。
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.html		0Kb	HTML	519	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

資料載入中.....