On the Detection of Footsteps Based on Acoustic and Seismic Sensing

In this work, we present a copula-based framework for integrating signals of different but statistically correlated modalities for binary hypothesis testing problems. Specifically, we consider the problem of detecting the presence of a human using footstep signals from seismic and acoustic sensors. An approach based on canonical correlation analysis and copula theory is employed to establish a likelihood ratio test. Experimental results based on real data are presented.