A Privacy-Protecting Step-Level Walking Direction Detection Algorithm Based on Floor Vibration

We present an algorithm and measurement system to detect the walking direction of persons based on ground vibrations. The approach is privacy-preserving because it solely relies on piezoelectric sensors built into the floor. Therefore, our system can be used in areas where cameras are not allowed or cannot capture the entire area. We present and compare our two innovative methods to analyze the ground vibrations caused by footsteps: the multipeaks average algorithm (MPAA) and the multipeaks averaged feature with a deep neural network-based classifier (MPAF-DNNC). MPAA judges the walking direction of pedestrians by analyzing the time-space relationship of at least two consecutive footstep vibration signals from multiple sensors. MPAF-DNNC receives multipeaks averaged feature as input and uses a deep neural network-based classifier to judge walking direction. Our experiments and evaluation show that our system can correctly determine the walking direction based on only three input step events (SEs) and provides an average F1 score of 0.97. When more than five SEs are inputted, the proposed system can correctly determine the walking direction with an average F1 score of 1.00.