Acoustic Gait-based Person Identification using Hidden Markov Models

We present a system for identifying humans by their walking sounds. This problem is also known as acoustic gait recogni-tion. The goal of the system is to analyse sounds emitted by walking persons (mostly the step sounds) and identify those per-sons. These sounds are characterised by the gait pattern and are influenced by the movements of the arms and legs, but also de-pend on the type of shoe. We extract cepstral features from the recorded audio signals and use hidden Markov models for dy-namic classification. A cyclic model topology is employed to represent individual gait cycles. This topology allows to model and detect individual steps, leading to very promising identi-fication rates. For experimental validation, we use the publicly available TUM GAID database, which is a large gait recognition database containing 3 050 recordings of 305 subjects in three variations. In the best setup, an identification rate of 65.5 % is achieved out of 155 subjects. This is a relative improvement of almost 30 % compared to our previous work, which used vari-ous audio features and support vector machines. Index Terms: Acoustic gait-based person identification, gait recognition, hidden Markov model