Radar-Based Continuous Human Activity Recognition with Multi-Label Classification

This paper presents a novel approach to radar-based human activity recognition in continuous data streams. To date, most work in this research area has aimed at either classifying every single time step separately by means of recurrent neural networks, or using a two-step procedure of first segmenting the stream into single activities and then classifying the segment. The first approach is restricted to time-dependent data as input; the second approach depends crucially on the segmentation step. To overcome these issues we propose a new approach in which we first segment the stream into windows of fixed length and subsequently classify each segment. Since due to the fixed length, the segment is not restricted to one activity alone, we use a multi-label classification approach, which can account for multiple activities taking place in the same segment by giving multiple outputs. To obtain a higher classification accuracy we fuse several radar data representations, namely range-time, range-Doppler and spectrogram. Using a publicly available dataset, an overall classification accuracy of 95.8% and F1 score of 92.08% could be achieved with the proposed method.