Unobtrusive High-Generalization Fall Detection: A Domain-Generalization Framework

It is essential to find and treat the elderly in time after they fall. A millimeter-wave radar sensor not only solves the problem of invasion of privacy caused by the camera but also avoids letting patients wear wearable devices, which has received more and more attention in the field of fall detection and motion recognition. Due to the different modulations of radar signals by different users and environments, the performance of the fall detection model is inevitably reduced. In this article, we propose a highly generalized radar-based fall detection framework to improve the generalization of the fall detection system in the new domain. We use a feature extractor with a ResNet structure constructed from 3-D convolution to extract features of the signal and a multilayer perceptron as a classifier for fall detection. We measure the cross-domain cross entropy of the features by setting subclassifiers for each domain to measure the cross-domain invariance of the features, enabling the feature extractor to extract domain-invariant features. We propose a specific data augmentation technology for radar time-series signals, which is combined with the proposed model to achieve more generalized fall detection. We have conducted sufficient experiments to explore the relationship between the number of users and domains and the model's generalization. The proposed method achieves an {F}1 score of 0.9747 on the proposed dataset containing ten scenarios, 21 subjects, 52 nonfalling actions and 12 falling actions, and an {F}1 score of 0.9949 on the public dataset, which shows superior effectiveness.