Deep Deconvolution Applied to Distributed Acoustic Sensing for Traffic Analysis

Distributed Acoustic Sensing (DAS) is a nascent technology that facilitates the measurement of vibrations along fibre-optic telecommunication cables, which has numerous novel applications in many domains of science and engineering. In the present study, we use DAS to analyse traffic along a fibre-optic cable deployed along a major road in Nice, France. We recently proposed to use a MUSIC beamforming algorithm for the objective of estimating the speed of individual vehicles. To greatly improve the accuracy and precision of the beamforming results, we here propose a Deep Deconvolution algorithm applied to the data prior to beamforming. The accuracy of the speed estimation is in the range of 0.14-0.25 km h
⁻¹
, which is at least one order of magnitude better than conventional methods. DAS therefore has great potential in urban traffic analysis applications.