Afitness: Fitness Monitoring on Smart Devices via Acoustic Motion Images

Recently, as fitness has become an popular part of people’s lives, the intention of recording fitness process and assessing the standard of fitness movements has grown increasingly keen. However, the existing approaches have some limitations, e.g., wearable devices can hinder users’ fitness activities; computer vision-based solutions pose the risk of privacy breach, etc. Fortunately, we observed that smart speaker, acoustic-based sensing, rises as a promising solution for activity monitoring. In this paper, we propose Afitness, an acoustic-based sensing system that enables non-intrusive, passive, and high-precision fitness detection. Afitness has the following three innovations: i)We utilize pulse compression to generate high-precision motion distance images on commercial devices, that can be visually recognized. ii) We propose a data augmentation algorithm, which also incorporates transfer learning to greatly reduce the pressure of data collection. iii) We exploit incremental learning techniques that allow Afitness to improve the portability of our system and recognize new actions. Overall, Afitness achieve acoustic signal interpretability and environmental reliability detection.