RF Signal Based Classification of Number of People in an Environment: A Machine Learning Approach
People Counting, Radio Frequency, USRP, Machine Learning.
This work proposes a technique for counting people in an already populated environment. Initially, a survey is made of the technologies and solutions designed for this purpose. As a proof of concept, a counting solution is analyzed for a small number of people, applying machine learning to the descriptive statistics of an RF signal. Finally, the classification results are presented for a more realistic scenario, with up to 350 people in the environment, using a software-defined radio measurement system for data collection. The results show significant precision in counting the number of people by classification in groups of individuals.