慣性感測器用於捷泳划手次數分析

Use inertial sensor for counting crawl strokes

呂子修(Tzu-Hsiu Lu)

指導教授 ： 潘孟鉉 ； 黃谷臣

淡江大學/工學院/資訊工程學系碩士班/碩士(2015年)

https://doi.org/10.6846/TKU.2015.00027

摘要

在游泳動作分析之領域中，選手之單趟游泳划手次數為一重要之參數，該參數可用以推估選手游泳速度、划手頻率、划手距離等游泳效率參數，然而我們發現到時下之以影像或是以動力學為基礎之游泳分析方法的設備需求高且不易於選手平時訓練使用。在本論文中我們提出一個適用於捷泳動作之計算划手次數的方法，所提出之方法僅需選手配戴慣性感測器即可準確地計算划手次數，我們的方法主要分成兩個階段，首先第一階段為感測資料處理階段，此階段蒐集慣性感測器線性加速度、過濾雜訊資料，以及求取特徵感測點，第二階段為划手動作切割階段，在此階段中，我們採用相關係數的概念，來判斷線性加速度資料中是否有相似的趨勢和計算划手次數。我們將所設計的方法實作於Android平台上，實驗結果顯示所提出之方法能夠準確地切割出划手區段和計算划手次數。

關鍵字

動作分析 ； 感測數據分析 ； 慣性感測器

並列摘要

In the field of swimming motion analysis, the number of strokes in a single trip is an important parameter. This parameter can be used to infer the speed of swimming, stroke rate, distance per stroke, and swim efficiency. However, we found that the current arts for analyzing need expensive equipment and cannot be used when training. In this paper, we propose an algorithm for calculating the number strokes of front crawl by wearable inertial devices. Our approach can be divided into two phases. The first one is the sensory data processing phase. In this phase, we gather the inertial sensory values, filter noises, and find feature points. The second phase is the stroke dividing phase. In this phase, we adopt the concept of correlation coefficient concept to judge if the collected linear acceleration values have similar tendencies and then to accumulate strokes. We implement our design on an Android platform. The experiment results indicate that the proposed scheme can precisely dividing sensory values into strokes and calculate number of strokes.

並列關鍵字

posture analysis ； sensory data analysis ； inertial sensors

參考文獻

[2]P. Siirtola, P. Laurinen, J. Röning, and H. Kinnunen. Efficient accelerometer-based swimming exercise tracking. In Proc. of IEEE Symposium on Computational Intelligence and Data Mining (CIDM), 2011.

[3] R. M. Hagem, S. G. O'Keefe, T. Fickenscher, and D. V. Thiel. Self-contained adaptable optical wireless communications system for stroke rate during swimming. IEEE Sensors Journal, 13(8):3144- 3151, 2013.

[4] F. Dadashi, F. Crettenand, G. P. Millet, and K. Aminian. Front-crawl instantaneous velocity estimation using a wearable inertial measurement unit. Sensors, 12(10):12927- 12939, 2012.

[5] A. Stamm, D. A. James, and D.V. Thiel. Velocity profiling using inertial sensors for freestyle swimming. Sports Engineering, 16(1):1-11, 2013.

[6] M. Bächlin, and G. Tröster. Swimming performance and technique evaluation with wearable acceleration sensors. Pervasive and Mobile Computing, 8(1):68-81, 2012.