On the Use of Low-Cost Radars and Machine Learning for In-Vehicle Passenger Monitoring

In this paper, we use a low-cost low-power mm-wave frequency modulated continuous wave (FMCW) radar for in-vehicle occupant monitoring. We propose an algorithm to identify occupied seats. Instead of using a high-resolution radar which increases the cost and area, we integrate machine learning algorithms with the results of covariance-based angle of arrival estimation Capon beamformer. We apply three classifiers, support vector machine (SVM), K-Nearest Neighbors (KNN) and Random Forest (RF). Our proposed system using SVM classifier achieved 96% accuracy on average in identifying the occupied seats in the test vehicles.