P2P-Insole: Human Pose Estimation Using Foot Pressure Distribution and Motion Sensors

TL;DR

P2P-Insole addresses privacy and cost barriers in 3D pose estimation by fusing plantar pressure data from embroidery-based insoles with IMU measurements and a Transformer for temporal modeling. It introduces a low-cost insole with 35 sensors costing under $1 and demonstrates that adding first and second derivatives to the input improves dynamic motion capture. Using synchronized OptiTrack ground-truth, insole pressure, and ankle IMU data, the Transformer outperforms a baseline LSTM in accuracy, reducing $RMSE$ across joints for several actions, especially dynamic motions. The work offers a scalable, privacy-preserving alternative to vision-based systems for rehabilitation, sports analytics, and continuous health monitoring, with future plans to reduce sensor count and broaden motion diversity.

Abstract

This work presents P2P-Insole, a low-cost approach for estimating and visualizing 3D human skeletal data using insole-type sensors integrated with IMUs. Each insole, fabricated with e-textile garment techniques, costs under USD 1, making it significantly cheaper than commercial alternatives and ideal for large-scale production. Our approach uses foot pressure distribution, acceleration, and rotation data to overcome limitations, providing a lightweight, minimally intrusive, and privacy-aware solution. The system employs a Transformer model for efficient temporal feature extraction, enriched by first and second derivatives in the input stream. Including multimodal information, such as accelerometers and rotational measurements, improves the accuracy of complex motion pattern recognition. These facts are demonstrated experimentally, while error metrics show the robustness of the approach in various posture estimation tasks. This work could be the foundation for a low-cost, practical application in rehabilitation, injury prevention, and health monitoring while enabling further development through sensor optimization and expanded datasets.

Figures (9)

• Figure 1: System Design
• Figure 2: Insole Sensor Design and Non-Inverting Amplifier Circuit
• Figure 3: Experimental Setup
• Figure 4: Transformer Architecture
• Figure 5: Highly accurate instantaneous predicted 3D skeleton.