milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
This work addresses privacy concerns in smart home applications by using mmWave radar instead of cameras for human motion sensing, though it is incremental as it builds on existing scene flow estimation techniques.
The paper tackles the problem of human motion sensing in smart homes by proposing milliFlow, a deep learning method for estimating scene flow from mmWave radar point clouds, which improves privacy over cameras. Experimental results show superior performance compared to competing approaches, with remarkable improvements in human activity recognition and human parsing, and support for human body part tracking.
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.