DIAT-μ RadHAR (Micro-Doppler Signature Dataset) & μ RadNet (A Lightweight DCNN)—For Human Suspicious Activity Recognition

In the view of national security, radar micro-Doppler (m-D) signatures-based recognition of suspicious human activities becomes significant. In connection to this, early detection and warning of terrorist activities at the country borders, protected/secured/guarded places and civilian violent protests is mandatory. Designing an automated human suspicious activities: army crawling, army jogging, jumping with holding a gun, army marching, boxing, and stone-pelting/grenades-throwing, recognition system using a suitable deep convolutional neural network (DCNN) model is rapidly growing due to its inherent in-depth features extraction capability. As a value addition to this research, an X-band continuous wave (CW) 10 GHz radar has been developed at our radar systems laboratory and used to acquire the m-D signatures, to prepare a dataset (DIAT-
$\mu $
RadHAR) corresponding to above mentioned suspicious activities. In order to prepare a realistic dataset, human targets of different heights, weights, and gender are directed to perform the suspicious activities in front of the radar at different ranges between 10 m - 0.5 km and at different target aspect angles (0°, ±15°, ±30° and ±45°). A lightweight DCNN architecture (
$\mu $
RadNet) is also designed and trained with the prepared DIAT-
$\mu $
RadHAR dataset comprising 3780 samples. The performance and recognition accuracy of
$\mu $
RadNet is statistically computed, and the results are compared to the state-of-the-art (SOTA) CNN models. The
$\mu $
RadNet DCNN model outperforms the SOTA CNN models, giving 99.22% of overall classification accuracy, 0.09M parameters, and 0.40G floating point operations (FLOPs) with minimal false negative/positive rates. The time-complexity of the designed lightweight
$\mu $
RadNet DCNN model is 0.12 s, which evidences the suitability of our DCNN model for the on-device implementation.