No abstract

No abstract

No abstract

In this paper, we tackle the task of multi-target tracking of humans in an indoor setting using a low power 77 GHz MIMO CMOS radar. A drawback of such a highresolution and low-power device is the higher sensitivity to noise, which makes the analysis of signals more challenging. Therefore, a pipeline is proposed to address both pre-processing of the radar signal and multi-target tracking. In the pre-processing phase, we focus on handling the low Signal-to-Noise Ratio (SNR) and eliminating so-called ghost targets. The tracking method we propose is based on Markov Chain Monte Carlo Data Association (MCMCDA), thus taking a combinatorial approach towards the task of tracking. The pipeline is tested on a number of real-world scenarios and shows promising results, overcoming the significant amount of noise associated with embedded radar devices.