SCL-Fall: Reliable Fall Detection Using mmWave Radar With Supervised Contrastive Learning

Fall is a severe health threat for elders' health care. While existing systems could achieve promising performance under specific scenarios, the required computing resources are usually not affordable, which is not applicable for real-time detection. In this article, we propose SCL-Fall, a real-time fall detection system using millimeter wave signal with supervised contrastive learning, which can achieve impressive accuracy with low computation complexity. Specifically, we first extract the signal variation corresponding to human activity with spatial–temporal processing. We incorporate reweighting and denoising techniques in the signal processing process. To enhance the system performance and robustness, we perform data augmentation by shifting, flipping, extracting, and interpolating the signal. Finally, we design a lightweight convolutional neural network to achieve real-time fall detection. Extensive experimental results demonstrate that the proposed system could achieve state-of-the-art performance with limited computation complexity.