Published

mmPose-FK: A Forward Kinematics Approach to Dynamic Skeletal Pose Estimation Using mmWave Radars

S. Hu, S. Cao, N. Toosizadeh, J. Barton, M. G. Hector, M. J. Fain

IEEE Sensors Journal, 2024 , Vol. 24 (5) , pp. 6469-6481

Abstract

This paper presents mmPose-FK, a novel approach for human pose estimation using millimeter-wave (mmWave) radar combined with dynamic forward kinematics constraints. The method addresses challenges of low resolution, specularity, and noise artifacts common to mmWave radars by integrating FK into a deep learning model for more stable and accurate pose estimation.

Citation

S. Hu, S. Cao, N. Toosizadeh, J. Barton, M. G. Hector, M. J. Fain. "mmPose-FK: A Forward Kinematics Approach to Dynamic Skeletal Pose Estimation Using mmWave Radars." IEEE Sensors Journal 24(5): 6469-6481, 2024. DOI: 10.1109/JSEN.2023.3348199

Related Projects

Human Pose Estimation

mmPose-FK: dynamic forward kinematics with deep learning for stable radar-based pose tracking

Quick Links

Publisher

Details

Year: 2024
Published In: IEEE Sensors Journal
Volume: 24
Issue: 5
Pages: 6469-6481
DOI: 10.1109/JSEN.2023.3348199

Back to Publications