PCFEx: Point Cloud Feature Extraction for Graph Neural Networks

2026-02-15

IEEE Internet of Things Journal

AI Summary

This work addresses the limited feature representation capability of millimeter-wave radar 3D point clouds in human pose estimation (HPE) and human activity recognition (HAR) by proposing a novel multi-level graph neural network architecture. For the first time, the approach systematically integrates features at the node, edge, and graph levels by treating the point cloud as a graph structure and introducing dedicated feature extraction mechanisms that effectively fuse multi-scale geometric and semantic information. Experimental results demonstrate that the proposed method significantly reduces estimation error across three HPE benchmarks and achieves a state-of-the-art accuracy of 98.8% on HAR tasks, outperforming existing advanced models.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Graph neural networks (GNNs) have gained significant attention for their effectiveness across various domains. This study focuses on applying GNN to process 3-D point cloud data for human pose estimation (HPE) and human activity recognition (HAR). We propose novel point cloud feature extraction (PCFEx) techniques to capture meaningful information at the point, edge, and graph levels of the point cloud by considering point cloud as a graph. Moreover, we introduce a GNN architecture designed to efficiently process these features. Our approach is evaluated on four most popular publicly available millimeter-wave radar datasets—three for HPE and one for HAR. The results show substantial improvements, with significantly reduced errors in all three HPE benchmarks, and an overall accuracy of 98.8% in mmWave-based HAR, outperforming the existing state-of-the-art models. This work demonstrates the great potential of feature extraction incorporated with GNN modeling approach to enhance the precision of point cloud processing.

Problem

• Point Cloud
• Graph Neural Networks
• Human Pose Estimation
• Human Activity Recognition
• Feature Extraction

Innovation

• Point Cloud Feature Extraction
• Graph Neural Networks
• Human Pose Estimation
• Human Activity Recognition
• Multi-level Graph Representation