Machine Learning Methods for Radar-Based People Detection and Tracking

This paper describes the work developed towards the implementation of a radar-based system for people detection and tracking in indoor environments using machine learning techniques. For such, a series of experiments were carried out in an indoor scenario involving walking people and dummies representative of other moving objects. The applied machine learning methods included a neural network and a random forest classifier. The success rates (accuracies) obtained with both methods using the experimental data sets evidence the high potential of the proposed approach.