A Spatiotemporal Attention Network for mmWave-Based 3-D Human Skeleton Estimation
- 30 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 44363-44377
Abstract
This article presents a spatiotemporal attention framework for radar-based human pose estimation (STAR-Pose), a unified model for estimating 3-D skeletal coordinates directly from millimeter-wave (mmWave) radar point clouds. The framework integrates PointNet++ for spatial feature extraction and a bidirectional long short-term memory (BiLSTM) module enhanced by attention pooling for temporal modeling. Data were collected using a selfdeveloped BHYY_MMW6044 radar operating in the 59–64-GHz band, capturing dynamic human motion in diverse scenarios. Comprehensive experiments demonstrate that STAR-Pose achieves an average localization error of 1.76 cm, outperforming existing radar-based baselines. The framework exhibits strong robustness to noisy frames, varying motion speeds, and cross-subject conditions, while maintaining stable accuracy under occlusion and multipath interference. Overall, STAR-Pose provides a reliable and privacy-preserving approach for human pose estimation with mmWave radar, paving the way for intelligent sensing applications in smart healthcare, ambient monitoring, and human–computer interaction.Keywords
Funding Information
- “Pioneer” and “Leading Goose” Research and Development Program of Zhejiang Province (2023C01148)
- Hangzhou Leading Innovation and Entrepreneurship Team (TD2022006)
This publication has 39 references indexed in Scilit:
- Spatial adaptive graph convolutional network for skeleton-based action recognitionApplied Intelligence, 2023
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition2019
- Simple Baselines for Human Pose Estimation and Tracking2018
- Through-Wall Human Pose Estimation Using Radio Signals2018
- Towards Accurate Multi-person Pose Estimation in the Wild2017
- DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model2016
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation2016
- Using k-Poselets for Detecting People and Localizing Their Keypoints2014
- Real-time human pose recognition in parts from single depth images2011
- Strike a Pose: Tracking People by Finding Stylized Poses2005