Road-Speed Estimation Using Convolutional Neural Networks and Simulated ϕ-OTDR Traces
Robson Assis Colares, Darli Mello

DOI: 10.14209/sbrt.2022.1570812396
Evento: XL Simpósio Brasileiro de Telecomunicações e Processamento de Sinais (SBrT2022)
Keywords: Distributed fiber optic sensing Phase-sensitive optical time-domain reflectometer Convolutional neural network classifier Road-speed estimation
We investigate distributed fiber optic sensing and machine-learning-based image analysis for road-speed estimation. Synthetic phase-sensitive optical time-domain reflectometer (ϕ-OTDR) traces are generated by the simulation of random road features such as car density and speed. Consecutive ϕ-OTDR traces are stacked generating images that are submitted to a convolutional neural network (CNN) for classification. The evaluated CNN-based classifier exhibits high accuracy at sufficiently high car densities.