# Human motion recognition and prediction using loose cloth

## TL;DR

This paper shows that sensors in loose clothing can accurately predict human motion, offering a more comfortable alternative to traditional body-attached sensors.

## Contribution

The study introduces the use of garment-embedded sensors for motion analysis, showing improved accuracy and reduced data requirements.

## Key findings

- Sensors in fabric improved motion recognition accuracy by up to 40%.
- The method required 80% less movement history than body-attached sensors.
- Garment motion provides valuable data for analyzing human movement.

## Abstract

Human motion analysis plays a crucial role in fields such as healthcare, human-robot interaction and virtual reality. Conventional approaches typically rely on tightly attached body sensors, which can prove uncomfortable and impractical. Here, we investigate motion recognition and prediction using garments incorporating embedded sensors. We analyse how the movement of loose-fitting clothing can predict body motion in both simulated and real-world scenarios. Results demonstrate that sensors attached to fabric can improve recognition accuracy by up to 40% improvement and require approximately 80% less movement history compared to sensors directly attached to the body. These findings indicate that garment motion provides valuable information for analysing human movement. The study additionally offers insights regarding the design of intelligent textiles with integrated sensing capabilities.

Conventional methods for human motion analysis using sensors tightly attached to the body are often uncomfortable. Here, the authors demonstrate motion recognition and prediction using sensors embedded in garments. The results provide guidance for the development of wearable technology integrated into everyday clothing.