Posture Tracking Meets Fitness Coaching: A Two-Phase Optimization Approach with Wearable Devices
Han Zhou, Yi Gao, Wenxin Liu, Yuefang Jiang, Wei Dong
Abstract
Fitness training is becoming an increasingly popular way of maintaining overall health and preventing illness. However, in some cases the training could be risky and fitness-related injuries have increased by 48% in the USA. The training itself will not cause hurt, but if it is performed in a crucial-improper form (using the wrong technique), it will injure the exerciser. Research has explored the potential of using wearables to monitor fitness training, but the consideration of proper/improper form is not included. In this paper, we propose WearCoach, a wearable based fitness training assistant, which acquires the user's fitness form information and generates real-time feedback during training. WearCoach differs from previous work of training assistant in 1) it employs a two-phase tracking algorithm to achieve accurate and real-time tracking of body motion, 2) it analyzes the captured arm posture and generates training guidance based on the user's form, 3) it uses joint orientation as an exercise classification feature to improve recognition accuracy. We conducted experiments with eight participants and nine exercises. Three kinds of feedback are generated, including injury alert, movement correction and symmetry analysis.