No Vision, No Wearables: 5G-based 2D Human Pose Recognition with Integrated Sensing and Communications

TL;DR

This paper introduces a novel 5G-based integrated sensing and communication system that accurately recognizes 2D human poses indoors without using vision or wearables, addressing privacy and occlusion issues.

Contribution

It presents a practical 5G ISAC system that infers 2D human poses from uplink signals, combining multi-domain features for improved indoor human pose recognition.

Findings

Outperforms existing vision and RF-based methods in indoor environments

Achieves high accuracy in 2D human pose recognition

Provides a privacy-preserving, contactless interaction solution

Abstract

With the increasing maturity of contactless human pose recognition (HPR) technology, indoor interactive applications have raised higher demands for natural, controller-free interaction methods. However, current mainstream HPR solutions relying on vision or radio-frequency (RF) (including WiFi, radar) still face various challenges in practical deployment, such as privacy concerns, susceptibility to occlusion, dedicated equipment and functions, and limited sensing resolution and range. 5G-based integrated sensing and communication (ISAC) technology, by merging communication and sensing functions, offers a new approach to address these challenges in contactless HPR. We propose a practical 5G-based ISAC system capable of inferring 2D HPR from uplink sounding reference signals (SRS). Specifically, rich features are extracted from multiple domains and employ an encoder to achieve unified alignment and representation in a latent space. Subsequently, low-dimensional features are fused to output the human pose state. Experimental results demonstrate that in typical indoor environments, our proposed 5G-based ISAC HPR system significantly outperforms current mainstream baseline solutions in HPR performance, providing a solid technical foundation for universal human-computer interaction.