用毫米波雷达点云做人体姿态估计，性能超越现有方法
mmGAT: Pose Estimation by Graph Attention with Mutual Features from mmWave Radar Point Cloud
- 结合图注意力网络与雷达点云，捕捉人体关节细节
- 在两个公开数据集上实现35.6%的定位误差降低
- 适合隐私敏感或低光环境下的姿态识别应用
人体姿态估计与人类动作识别（HAR）是多个领域的核心技术。尽管基于图像的方法表现优异，但在隐私保护和低光照环境下表现不佳。本文利用毫米波（mmWave）雷达技术，通过图神经网络（GNN）与注意力机制处理雷达点云数据，提升姿态估计精度。提出一种独特的特征提取方法，充分发挥GNN在点云建模中的潜力。所提出的mmGAT模型在两个公开的毫米波雷达基准数据集上表现卓越，多数场景下达到新最优结果。相比当前最优基准，其姿态估计均方关节位置误差（MPJPE）降低35.6%，旋转平均关节位置误差（PA-MPJPE）降低14.1%。
原文摘要 · Abstract (English)
Pose estimation and human action recognition (HAR) are pivotal technologies spanning various domains. While the image-based pose estimation and HAR are widely admired for their superior performance, they lack in privacy protection and suboptimal performance in low-light and dark environments. This paper exploits the capabilities of millimeter-wave (mmWave) radar technology for human pose estimation by processing radar data with Graph Neural Network (GNN) architecture, coupled with the attention mechanism. Our goal is to capture the finer details of the radar point cloud to improve the pose estimation performance. To this end, we present a unique feature extraction technique that exploits the full potential of the GNN processing method for pose estimation. Our model mmGAT demonstrates remarkable performance on two publicly available benchmark mmWave datasets and establishes new state of the art results in most scenarios in terms of human pose estimation. Our approach achieves a noteworthy reduction of pose estimation mean per joint position error (MPJPE) by 35.6% and PA-MPJPE by 14.1% from the current state of the art benchmark within this domain.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。