12 May 2016 Using convolutional neural networks for human activity classification on micro-Doppler radar spectrograms
Author Affiliations +
Abstract
This paper presents the findings of using convolutional neural networks (CNNs) to classify human activity from micro-Doppler features. An emphasis on activities involving potential security threats such as holding a gun are explored. An automotive 24 GHz radar on chip was used to collect the data and a CNN (normally applied to image classification) was trained on the resulting spectrograms. The CNN achieves an error rate of 1.65 % on classifying running vs. walking, 17.3 % error on armed walking vs. unarmed walking, and 22 % on classifying six different actions.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tyler S. Jordan, "Using convolutional neural networks for human activity classification on micro-Doppler radar spectrograms", Proc. SPIE 9825, Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security, Defense, and Law Enforcement Applications XV, 982509 (12 May 2016); doi: 10.1117/12.2227947; https://doi.org/10.1117/12.2227947
PROCEEDINGS
9 PAGES


SHARE
Back to Top