Exercise speed is a crucial indicator in bodyweight exercise assessment, directly reflecting muscular strength, energy expenditure, and exercise power. Benefiting from ubiquitous infrastructure and non-intrusive properties, WiFi-based sensing has emerged as a promising technique for motion speed estimation. However, existing WiFi sensing systems are significantly influenced by user diversity, positional variations, and orientation changes, which limit their applicability in real-world scenarios. In this work, we propose a learning-based framework, named SpeedFi , to estimate exercise speed from WiFi Channel State Information (CSI). An encoder-decoder network is designed to infer body speed, while temporal–frequency constraints are introduced to model consistent speed dynamics. To enhance user generalization, a domain adversarial strategy is adopted to extract user-invariant features. Moreover, two orthogonal WiFi links are deployed to capture complementary spatial perspectives, and an attention-based fusion module is employed for effective feature integration. A physics-inspired simulation model is further developed to synthesize CSI frequency variations, guiding the design of a diversified data collection strategy covering multiple positions, orientations, and environmental configurations. We conduct extensive experiments involving 10 participants performing 3 types of bodyweight exercises across 5 distinct environments. In controlled settings, SpeedFi achieves an average speed estimation error of 0.113 m/s for peak speeds around 1 m/s. Real-time analysis indicates that the system runs at over 40 FPS on a mid-range GPU, supporting its potential for real-time deployment. Additional tests under multi-person scenarios, complex multipath conditions, and varying WiFi link configurations are conducted to assess the system’s operational boundaries and robustness, validating its applicability across diverse settings.
Gao et al. (Wed,) studied this question.