LW-μDCNN: A Lightweight CNN Model for Human Activity Classification using Radar micro-Doppler Signatures

Recognition of human activities plays a pivotal role in recent times for surveillance and security. The convolution neural network (CNN) based models are growing to classify human activities using micro- Doppler
$(\mu\mathbf{D})$
signatures. However, a larger number of parameters of the CNN models increases the computation cost and increases the size. The present work introduces a novel lightweight model, “LW
$-\mu$
DCNN,” to classify human activities. The architecture of LW
$-\mu$
DCNN has 438998 parameters with 7 layers. A total of six human activities are recorded in the FM CWR dataset, which is in the form of
$\mu\mathbf{D}$
signatures. These
$\mu \mathbf{D}$
signatures are converted into spectrogram images and are considered as input for the experiments. The size of the LW
$-\mu$
DCNN model is only 5.2 MB, which is further optimized by considering quantization aware training, “QAT-LW-
$\mu$
DCNN,” has size of 0.43 MB with minimal loss of accuracy. The extensive analysis shows that the LW
$-\mu$
DCNN model achieves 97% of classification accuracy with a higher F1-score for every class than the other state-of-the-art models. The present paper also proposed two transfer learning approaches, i.e., InceptionV3 and MobileNetV1, for the experimental studies to classify human activities.