DeepActivity: a micro-Doppler spectrogram-based net for human behaviour recognition in bio-radar

Abstract

The movements of the human body and limbs result in unique micro-Doppler signatures, which can be exploited for classifying human activities. In this work, the authors propose a Convolutional Gated Recurrent Units Neural Network (CNN-GRU) to classify human activities of varying duration based on micro-Doppler spectrogram. Unlike conventional deep learning approaches which often treat the micro-Doppler spectrogram the same way as natural image, the authors extract local feature of micro-Doppler signatures via convolutional layer and encode temporal information with gated recurrent units. Through this unified framework, the temporal evolution of body motions within a short time can be better utilised. It avoids the resolution limitation caused by the fixed-size time window of input data and identifies human activity of duration shorter than the time window length. The experiment shows that CNN-GRU model is capable of recognising and temporally localising activity sequence contained in the spectrogram.

Keywords

• feature extraction
• image classification
• Doppler radar
• recurrent neural nets
• radar imaging
• convolutional neural nets
• image coding
• image motion analysis
• human behaviour recognition
• bio-radar
• human body
• limbs
• microDoppler signatures
• conventional deep learning approaches
• temporally localising activity sequence
• human activity classification
• activity sequence recognition
• DeepActivity
• microDoppler spectrogram-based net
• convolutional gated recurrent units neural Network
• local feature extraction
• convolutional layer
• CNN-GRU model