Free Weight Exercises Recognition Based on Dynamic Time Warping of Acceleration Data - Intelligent Computing for Sustainable Energy and Environment - page 178

Free Weight Exercises Recognition Based on Dynamic
Time Warping of Acceleration Data

Chuanjiang Li 1,2 , Minrui Fei 1 , Huosheng Hu 3 , and Ziming Qi 4

1 School of Mechanical Engineering & Automation, Shanghai Key Laboratory of Power Station
Automation Technology, Shanghai University, 200072, China
2 College of Information, Mechanical & Electrical Engineering, Shanghai Normal University,
Shanghai, 200234, China
3 Department of Computer Science, University of ESSEX, Colchester, UK, CO4 3SQ
4 School of Architecture Building & Eng., Otago Polytechnic, Dunedin, New Zealand, 9054
[e-mail], [e-mail], [e-mail],
[e-mail]

Abstract. To maximize training effects in free weight exercises, people need to
remember repetitions of each type of exercises, which is tedious and difficult.
Recognizing exercises type and counting automatically can overcome this
problem, and multiple accelerometers were used in the existing exercises
recognition. This paper presents a new recognition method based on one tri-
axial accelerometer, in which a filtered acceleration data stream is divided into
time series with unequal length for peak analysis instead of conventional fixed
length window. Based on this time series, Dynamic Time Warping (DTW) is
deployed to recognize weight exercise types. 3D Euclidean distance and Itakura
parallelogram constraint region are used to improve recognition performance. A
reference template is set up for each class based on many examples instead of
one in the conventional way. The proposed procedures are compared with other
popular methods with both the user-dependent protocol and the user-
independent protocol. Results show that proposed approach is feasible and can
achieve good performance.

Keywords: Free weight exercise, Dynamic time warping, Acceleration data.

1 Introduction

A recent research report reveals that 35.7% of American adults and 17% of American
children were obese [1]. To reduce obesity and other chronic diseases, such as
heart/cardiovascular diseases, diabetes, hypertension, etc., proper weight exercise
plays an important role [2-4]. However, no machine is currently available for tracking
the weight exercises, apart from specially designed treadmills and cycle machines.
Because the weight training involves many types of exercises, and each type should
be done in many repetitions, people may forget their progress or miscount the number
of repetition.
In [4], free-weight exercises are tracked based on two tri-axis accelerometers, in
which one is placed on the back of the hand and the other on the waist. The overall