Automatic counting methods applied to unspecified repetitive physical activities
DescriptionMeasuring physical activity using wearable sensors is important for quantifying adherence to exercise regiments in clinical research. An important aspect of wearable activity tracking is counting particular movements, such as steps. However, during physical therapy there are movements that are unique to the patient and also valuable to track. The aim of this work is to design an automatic counting system which is flexible enough to measure multiple distinct, repeating movements during physical therapy. Accelerometers, using smartphones, were attached to the body or held by participants to track repetitive motions during different exercises. 18 participants completed a series of ten exercises for 30 seconds, including arm circles, bicep curls, bridges, sit-ups, elbow extensions, leg lifts, lunges, push-ups, squats, and upper trunk rotations. To count the repetitions of each exercise we apply three analysis techniques: a) threshold crossing, b) threshold crossing with a low-pass filter, c) Fourier transform. The results demonstrate that arm circles and push-ups can be tracked well, while less periodic and irregular motions like upper trunk rotations are more difficult to analyze across techniques. Overall, the threshold crossing with low-pass filtering achieves the best performance among these methods. We conclude the proposed automatic counting system is capable of tracking a large number of unspecified physical activities, even ones for which the system was not originally designed.