跳到主要內容

臺灣博碩士論文加值系統

(3.235.120.150) 您好!臺灣時間:2021/08/03 07:04
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:董晏儒
研究生(外文):Yen-Ju Tung
論文名稱:基於使用者步頻的音樂輔助跑步系統
論文名稱(外文):Music Assisted Running Trainer Based on Runner’s Step Frequencies
指導教授:張智星張智星引用關係
指導教授(外文):Jyh-Shing Jang
口試委員:王新民鄭士康蘇黎
口試委員(外文):Hsin-Min WangShyh-Kang JengLi Su
口試日期:2015-07-14
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊網路與多媒體研究所
學門:電算機學門
學類:網路學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:英文
論文頁數:59
中文關鍵詞:步頻分析腳步偵測三軸加速度計陀螺儀
外文關鍵詞:step-per-minute analysisstep detectiontri-accelerometergyroscope
相關次數:
  • 被引用被引用:0
  • 點閱點閱:268
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文是有關於我們所開發出的一個手機應用程式 MART (Music Assisted Run Trainer),這個應用程式的目的是要利用控制音樂的節奏快慢來讓使用者可以跑得更輕鬆。MART可以透過使用者手機中的三軸加速度計跟陀螺儀,來即時推算出使用者的步頻,再藉由波形相似性疊加法的技術,來合成出與使用者步頻相同節奏的音樂。前人的腳步偵測研究,大都是採用閥值判斷的方法,但MART是使用一個類似音樂訊號處理中節拍追蹤的方法,來做腳步偵測跟步頻分析。本論文共提出了四種抓取步頻的方法,三種是使用時域上的自相關函數,最後一種則是使用頻域上的倒頻來做運算。我們設計了兩種實驗來驗證我們的系統,分別是對腳步預測的正確性,以及算出的步頻跟實際步頻的誤差值。最後根據實驗結果,我們發現時域的方法的正確性,都比頻域的方法來得高。

This thesis describes a smartphone app we developed called MART (Music Assisted Run Trainer). The goal is to assist users to jog easily and pleasantly through controlling the tempo of the music. MART estimates the runner’s SPM (steps-per-minute) in real-time via the tri-accelerometer and gyroscope in the smartphone. The music whose tempo is the same as the runner’s SPM is then synthesized via Waveform Similarity Based Overlap-Add (WSOLA). Most of the existing research in step detection uses threshold-based methods, while MART adopts a method which is based on a beat tracking algorithm. We propose four methods for finding the step period. Three of them are based on autocorrelation function in the time domain, while the other one is based on cepstrum in the frequency domain. We design two experiments to evaluate the performance of MART in detecting steps and estimating step frequency. Experimental result shows that the accuracy of the time-domain methods is better than the frequency-domain method.

口試委員審定書 i
誌謝 ii
摘要 iii
ABSTRACT iv
CONTENTS v
LIST OF FIGURES viii
LIST OF TABLES xi
Chapter 1 Introduction 1
Chapter 2 Related Work 4
2.1 Step Detection Methods 4
2.1.1 Gyroscope-based Algorithm 4
2.1.2 Accelerometer-based Algorithms 5
2.2 Commercial Products 11
2.2.1 Nike+ Running 11
2.2.2 TempoRun 12
2.2.3 Sony – Walkman NW-S200 Series 12
2.2.4 Sony – Smart B-Trainer 13
Chapter 3 Methods 14
3.1 System Overview 14
3.2 Beat Tracking 15
3.2.1 Fast Fourier Transform 15
3.2.2 Mel-Band Filter 16
3.2.3 Spectral Flux 18
3.2.4 Smoothing and Trend Removal via Gaussian Filter 20
3.2.5 Autocorrelation Function (ACF) 20
3.2.6 Detecting Beats 22
3.3 Step Tracking 24
3.3.1 Signal Types 26
3.3.2 Step Period Finding 27
3.3.1 Strength Curve 34
3.3.2 Steps Detecting 37
3.3.3 Step Predicting 37
3.4 Music Tempo Selection 39
3.5 Time-scale Modification of Music 40
3.6 Step Matching 40
Chapter 4 Experiment 41
4.1 Dataset 41
4.1.1 Collection Method 41
4.1.2 Data Content 41
4.1.3 GroundTruth Labeling 42
4.2 Parameter Setting 43
4.2.1 Signal & Onset Strength Curve 45
4.2.2 Method 1 – Correction by Last Step 47
4.2.3 Method 2 – Noise Removal 48
4.2.4 Method 3 – Cepstrum 49
4.2.5 Method 4 – All Signals 50
4.2.6 Step Frequency & Music Tempo 51
4.3 Experimental Result 53
Chapter 5 Conclusions & Future Works 55
5.1 Conclusions 55
5.2 Future Works 56
REFERENCE 58


[1]跑者廣場全國賽事統計 http://www.taipeimarathon.org.tw/contestnew.aspx
[2]Tokyo Marathon 2014 http://www.tokyo42195.org/2014en/past/index.html
[3]Terry, P. C., Karageorghis, C. I., Mecozzi Saha, A., & D’Auria, S, “Effects of synchronous music on treadmill running among elite triathletes” Journal of Science and Medicine in Sport, 15, 52-57. 2012.
[4]Pollster波仕特線上市調:【跑步收聽音樂習慣調查報告】http://www.pollster.com.tw/Aboutlook/lookview_item.aspx?ms_sn=2357
[5]S. Jayalath, N. Abhayasinghe, I. Murray, "A Gyroscope Based Accurate Pedometer Algorithm" , 2013 International Conference on Indoor Positioning and Indoor Navigation
[6]M. Tomlein, et al, “Advanced Pedometer For Smartphone-Based Activity Tracking”, 2012 International Conference on Health Informatics
[7]T. OlutoyinOshin, S. Poslad, “ERSP: An Energy-efficient Real-time Smartphone Pedometer”, 2013 IEEE Systems, Man, and Cybernetics Society
[8]"Nyquist–Shannon sampling theorem", n.d, in Wikipedia, retrieved June 20, 2015, from https://en.wikipedia.org/wiki/Nyquist–Shannon_sampling_theorem
[9]D. Sugimori, et al, "A Study about Identification of Pedestrian by Using 3-axis Accelerometer", 2011, 17th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications
[10]Jason A. Hockman ,et al, "Real-time Phase Vocoder Manipulation by Runner’s Pace", 2009 International Conference on New Interfaces for Musical Expression
[11]Nike+ Running, http://www.nike.com/us/en_us/c/running/nikeplus/gps-app
[12]TempoRun, http://www.temporunapp.com/
[13]Sony, Smart B-Trainer, http://smartsports.sony.net/b-trainer/product/1G/WW/en/
[14]SoundTouch Audio Processing Library, http://www.surina.net/soundtouch/
[15]W. Verhelst, M. Roelands, “An overlap-add technique based on waveform similarity (WSOLA) for high quality time-scale modification of speech”, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[16]Daniel P. W. Ellis, “Beat Tracking by Dynamic Programming”, Journal of New Music Research , vol. 36, no. 1, pp. 51-60, 2007
[17]Juan Pablo Bello, et al, "A Tutorial on Onset Detection in Music Signals", IEEE Transactions on speech and audio processing,2005


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top