Stretchable spring-sheathed yarn sensor for 3D dynamic body reconstruction assisted by transfer learning

Abstract

A wearable sensing system that can reconstruct dynamic 3D human body models for virtual cloth fitting is highly important in the era of information and metaverse. However, few research has been conducted regarding conformal sensors for accurately measuring the human body circumferences for dynamic 3D human body reshaping. Here, we develop a stretchable spring-sheathed yarn sensor (SSYS) as a smart ruler, for precisely measuring the circumference of human bodies and long-term tracking the movement for the dynamic 3D body reconstruction. The SSYS has a robust property, high resilience, high stability (>18 000), and ultrafast response (12 ms) to external deformation. It is also washable, wearable, tailorable, and durable for long-time wearing. Moreover, geometric, and mechanical behaviors of the SSYS are systematically investigated both theoretically and experimentally. In addition, a transfer learning algorithm that bridges the discrepancy of real and virtual sensing performance is developed, enabling a small body circumference measurement error of 1.79%, noticeably lower than that of traditional learning algorithm. Furtherly, 3D human bodies that are numerically consistent with the actual bodies are reconstructed. The 3D dynamic human body reconstruction based on the wearing sensing system and transfer learning algorithm enables excellent virtual fitting and shirt customization in a smart and highly efficient manner. This wearable sensing technology shows great potential in human-computer interaction, intelligent fitting, specialized protection, sports activities, and human physiological health tracking.