Urban Infrastructure

Footstep Vibration-Based Pedestrian Localization System

Automated and Scalable Footstep Vibration-Based Pedestrian Localization in Built Environments Using Deep Learning

We introduce a novel deep-learning-based footstep localization system using ground vibrations measured using geophones and a scalable method to automatically collect training data. We show that it significantly outperforms acoustic localization.

Pedestrian Footstep Localization Using a Deep Convolutional Network for Time Difference of Arrival Estimation

We present a privacy-preserving localization system that uses geophones to map pedestrian locations in outdoor spaces. The system uses a 1D-CNN to compute time differences of arrival (TDOA) and achieves localization accuracy of less than 1 meter.