Interferometric radar for activity recognition and benchmarking in different radar geometries

Abstract

Radar micro-Doppler signatures have been proposed for human activity classification for surveillance and ambient assisted living in healthcare-related applications. A known issue is the performance reduction when the target is moving tangentially to the line-of-sight of the radar. Multiple techniques have been proposed to address this, such as multistatic radar and to some extent, interferometric radar. A simulator is presented to generate synthetic data representative of 8 different radar systems (including configurations as monostatic, multistatic, and interferometric) to quantify classification performances as a function of aspect angles and deployment geometries. This simulator allows an unbiased performance evaluation of the different radar systems. 6 human activities are considered with signatures originating from motion-captured data of 14 different subjects. The results show that interferometric radar data with fusion outperforms the other methods with over 97.6% accuracy consistently across all aspect angles, as well as the potential for simplified indoor deployment.