You are here: Home / Research / Classifying Armed/Unarmed Personnel using Radar with over 95% accuracy

Classifying Armed/Unarmed Personnel using Radar with over 95% accuracy

2017 Premium Award for Best Paper in IET Radar, Sonar & Navigation

Congratulations to world leading radar expert Professor Hugh Griffiths who has just been awarded the 2017 Premium Award for Best Paper in IET Radar, Sonar & Navigation for his co-authored paper titled ‘Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro-Doppler’. The other authors were postdocs Dr Francesco Fioranelli (now at Glasgow University) and Dr Matthew Ritchie (IET Radar, Sonar & Navigation, Volume 10, Issue 9, December 2016, p. 1702 – 1710. - doi: 10.1049/iet-rsn.2015.0493 - http://digital-library.theiet.org/content/journals/10.1049/iet-rsn.2015.0493

fig_2_microdoppler Their study analyses the use of human micro-Doppler signatures collected using a multistatic radar system to identify and classify unarmed and potentially armed personnel walking within a surveillance area. The signatures were recorded in a series of experimental tests and analysed through short time Fourier transform followed by feature extraction and classification. The image shows calibration targets (sphere and trihedral corner reflector) used during the trials of the system, which were carried out at the UCL sports ground at Shenley.

The paper showed that classification accuracy above 95% can be achieved using a single feature. Features based on the centroid of the signatures are shown to be also effective in cases where there are two people walking together in the same direction and at similar speed, and one of them may be armed or not, i.e. for targets not easily separable in range or in Doppler.

169844.png