milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing

TL;DR

milliFlow is a deep learning method that estimates scene flow from mmWave radar point clouds, enhancing human motion sensing and activity recognition while preserving privacy.

Contribution

The paper introduces milliFlow, a novel deep learning approach for scene flow estimation on mmWave radar data, improving human motion analysis tasks.

Findings

Outperforms existing methods in scene flow estimation

Enhances human activity recognition accuracy

Supports human body part tracking

Abstract

Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose milliFlow, a novel deep learning approach to estimate scene flow as complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method when compared with the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition and human parsing and support human body part tracking. Code and dataset are available at https://github.com/Toytiny/milliFlow.