Diff-HPE: Multihypothesis Human Pose Estimation Based on mmWave Radar and Diffusion Framework
- 28 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (13) , 25185-25197
Abstract
Comparison to optical sensors, millimeter wave (mmWave) radar has advantages in scenarios with poor visibility or in the cases where privacy needs to be protected. Thus, it has been widely applied in human posture estimation for health monitoring or autonomous driving. However, the posture estimation using a single mmWave radar faces challenges such as low resolution, specularity, and noise artifacts in information extraction. To address these issues, we propose a novel human posture estimation method based on a diffusion framework, which is called as Diff-HPE. The Diff-HPE method employs a neural network denoising approach to reduce the noise in point clouds, and a multi-frame joint enhancement strategy based on motion sequence continuity to mitigate the sparsity and improve the stability. Furthermore, a diffusion model is used to extract the spatiotemporal details, enabling precise estimation of key human joints in indoor environments over long distance. Our comprehensive experiments demonstrate that the system can achieve efficient human pose estimation with an average localization error of 5.2 cm, exhibiting high accuracy and robustness even in the scenarios where the visual pathways are completely obstructed.Keywords
Funding Information
- China Postdoctoral Science Foundation (2023M730554, BX20220065)
- Natural Science Foundation of Jiangsu Province of China (BK20230816)
- National Natural Science Foundation of China (62288101, 62301146)
This publication has 40 references indexed in Scilit:
- milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing2024
- DBMHT: A double-branch multi-hypothesis transformer for 3D human pose estimation in videoComputer Vision and Image Understanding, 2024
- LMFormer: Lightweight and multi-feature perspective via transformer for human pose estimationNeurocomputing, 2024
- Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation2023
- DiffusionDet: Diffusion Model for Object Detection2023
- Deep learning-based estimation of whole-body kinematics from multi-view imagesComputer Vision and Image Understanding, 2023
- 3D Human Keypoints Estimation from Point Clouds in the Wild without Human Labels2023
- Flexible generation-on-demand multistation for non-cooperative 6DOF pose measurementPrecision Engineering, 2022
- DBSCAN Clustering Algorithm of Millimeter Wave Radar Based on Multi Frame Joint2022
- Diffusion Probabilistic Models for 3D Point Cloud Generation2021