Exploring the Feasibility of Full-Body Muscle Activation Sensing with Insole Pressure Sensors

TL;DR

This paper addresses the challenge of unobtrusively sensing full-body muscle activation in daily life, where traditional sEMG methods are impractical. It proposes Press2Muscle, a learning-based pipeline that maps foot pressure captured by insole sensors to eight muscle activations, using Region Importance Learning, FiLM-based biographical conditioning, and a transformer-based temporal model, augmented with pressure-specific data transformations. The method demonstrates strong cross-user generalization (RMSE ≈ 0.025) across 30 subjects and various real-world conditions, including different footwear and surfaces, and even unseen motions, while enabling muscle imbalance detection and in-situ monitoring. The work offers a scalable, privacy-preserving alternative for mobile health, rehabilitation, and personalized coaching, with real-time inference capabilities and potential integration into multimodal sensing frameworks.

Abstract

Muscle activation initiates contractions that drive human movement, and understanding it provides valuable insights for injury prevention and rehabilitation. Yet, sensing muscle activation is barely explored in the rapidly growing mobile health market. Traditional methods for muscle activation sensing rely on specialized electrodes, such as surface electromyography, making them impractical, especially for long-term usage. In this paper, we introduce Press2Muscle, the first system to unobtrusively infer muscle activation using insole pressure sensors. The key idea is to analyze foot pressure changes resulting from full-body muscle activation that drives movements. To handle variations in pressure signals due to differences in users' gait, weight, and movement styles, we propose a data-driven approach to dynamically adjust reliance on different foot regions and incorporate easily accessible biographical data to enhance Press2Muscle's generalization to unseen users. We conducted an extensive study with 30 users. Under a leave-one-user-out setting, Press2Muscle achieves a root mean square error of 0.025, marking a 19% improvement over a video-based counterpart. A robustness study validates Press2Muscle's ability to generalize across user demographics, footwear types, and walking surfaces. Additionally, we showcase muscle imbalance detection and muscle activation estimation under free-living settings with Press2Muscle, confirming the feasibility of muscle activation sensing using insole pressure sensors in real-world settings.

Figures (15)

• Figure 1: In contrast to traditional methods, Press2Muscle provides an unobtrusive and scalable solution for accurate full-body muscle activation monitoring with pressure insoles, unlocking broad applications in health and fitness.
• Figure 2: (a) The platform consists of multiple flexible film pressure sensors from two feet (b) with compact data collection boards that support wireless data streaming. (c) The platform can be seamlessly inserted into shoes with negligible impact on users' appearance and movements.
• Figure 3: An example of a user alternatively pushing his legs forward. (a) The captured activation of the quadriceps aligns with the role of knee extension, which is essential for pushing the leg forward (other muscle groups also get activated due to maintaining balance). (b) The pressure data present a coordinated pattern. (c) A video is recorded to justify the movements. Note that the heatmaps are generated from 36 channels of pressure data after Gaussian interpolation for visualization purposes.
• Figure 4: Press2Muscle Overview.
• Figure 5: Examples of proposed pressure augmentations.