Indoor Regional People Counting Method Based on Bi-Motion-Model-Framework Using UWB Radar
Zhaocheng Yang, Guanghao Qi, Runhan Bao
Abstract
In this letter, we propose a people counting method based on bi-motion-model-framework (BMMF) using ultra-wide bandwidth (UWB) radar. Because different people motion states (people standing still or moving) in indoor environments lead to significant fluctuations of the received radar signal, it will confuse the results of different cases and degrade the estimation accuracy of the people counting methods. Herein, we first attempt to extract the motion features, including activation index (AI), connected regions (CRs), and energy of frames (EoF), to distinguish the motion states of people. Then, we use the probabilistic model (PM) method or convolutional neural network (CNN) method to predict the number of people for the classified motion state model. Finally, the experimental results show that the proposed method significantly outperforms the PM-based and CNN-based methods without considering the motion states influences.