A Voxelization Algorithm for Reconstructing mmWave Radar Point Cloud and an Application on Posture Classification for Low Energy Consumption Platform

Abstract

Applications for millimeter-wave (mmWave) radars have become increasingly popular in human activity recognition. Many researchers have combined radars with neural networks and gained a high performance on various applications. However, most of these studies feed the raw point cloud data directly into the networks, which can be unstable and inaccurate under certain circumstances. In this paper, we define a reliability measure of the point cloud data and design a novel voxelization algorithm to reconstruct the data. Experiments show that our algorithm can improve the stability of the point cloud generated from mmWave radars in terms of error reduction and scene re-construction. We demonstrate the effectiveness of our proposed algorithm using a neural network-based system for identifying a person’s sitting direction. In our experiment, compared with the baseline, our voxelization algorithm can improve the system in terms of accuracy (4.3%), training time (55.6%), and computational complexity, which is more suitable for light-weighted networks and low energy consumption platforms.

Intelligent Millimeter-Wave System for Human Activity Monitoring for Telemedicine

“…However, the fluctuating count of cloud points in each frame from mmwave radar introduces challenges in crafting precise activity classifiers, as these typically require fixed input dimensions and order [ 35 ]. To address this, researchers commonly standardize the data into forms like micro-Doppler signatures [ 45 , 46 ], image sequences [ 47 , 48 , 49 ], or 3D voxel grids [ 19 , 50 ] before employing machine learning. This standardization often results in the loss of spatial features [ 51 ] and can cause data bloat and related challenges [ 20 ].…”

Four-Dimensional (4D) Millimeter Wave-Based Sensing and Its Potential Applications in Digital Construction: A Review

“…By analyzing the range and elevation information of radar signals reflected by the human body, 4D mmw radars are capable of recognizing various postures, such as standing, sitting, lying down, and bending [46,47]. Posture recognition can provide valuable insights into monitoring daily activities and the health status of elderly or disabled individuals, as well as help to detect falls or abnormal behaviors [48,49]. Figure 11 is an example of human posture tracking using a 4D mmw radar (performed by the authors of this paper), where the green and red points are 3D point clouds that interpreted from 4D mmw signals.…”