Enhanced Sparse Point Cloud Data Processing for Privacy-aware Human Action Recognition

TL;DR

This paper evaluates and enhances data processing methods for privacy-preserving human action recognition using sparse mmWave radar point clouds, providing insights into accuracy and computational trade-offs.

Contribution

It offers a comprehensive analysis of existing data processing techniques and proposes targeted improvements for better mmWave radar-based HAR performance.

Findings

Pairwise method combinations improve recognition accuracy.

Kalman Filtering offers a good balance of accuracy and efficiency.

Enhanced methods outperform baseline approaches in key metrics.

Abstract

Human Action Recognition (HAR) plays a crucial role in healthcare, fitness tracking, and ambient assisted living technologies. While traditional vision based HAR systems are effective, they pose privacy concerns. mmWave radar sensors offer a privacy preserving alternative but present challenges due to the sparse and noisy nature of their point cloud data. In the literature, three primary data processing methods: Density-Based Spatial Clustering of Applications with Noise (DBSCAN), the Hungarian Algorithm, and Kalman Filtering have been widely used to improve the quality and continuity of radar data. However, a comprehensive evaluation of these methods, both individually and in combination, remains lacking. This paper addresses that gap by conducting a detailed performance analysis of the three methods using the MiliPoint dataset. We evaluate each method individually, all possible pairwise combinations, and the combination of all three, assessing both recognition accuracy and computational cost. Furthermore, we propose targeted enhancements to the individual methods aimed at improving accuracy. Our results provide crucial insights into the strengths and trade-offs of each method and their integrations, guiding future work on mmWave based HAR systems