Neural Networks-Assisted PCF Interferometers for Smart Road Traffic Surveillance

Efficient road traffic monitoring has a significant impact on the social and economic welfare of modern cities. Hence, developing a sensitive detection system that identifies various features of moving vehicles in real-time could suffice the demand for an integrable and competent traffic surveillance network. In this work, we propose and demonstrate a combination of in-line fiber interferometer-based sensing probes to act as weigh-in-motion systems (WIMs) for active detection of vehicular flow. The interferometers are fabricated using solid core photonic crystal fiber (SCPCF) sections, whose sensitivity is tailored by varying the dimensions of the section and installation depth of the interferometers. The sensitive interferometry-based probes operate by wavelength interrogation and enable the detection of a wide range of vehicles, from bicycles to buses. To augment the functionality of the proposed WIMs, artificial neural network (ANN) models are developed that enable the determination of vehicle parameters such as average speed, weight, wheelbase, and class from the recorded temporal response of the sensing probes. The models perform accurately in determining the vehicle features, with the classification model having an average accuracy of 96%. The algorithms can be integrated with the Internet of Things (IoT) to establish a cloud-based traffic monitoring interface for civic departments and public utilities. The interferometry-enabled WIMs are tailorable and compatible with varied road conditions. Besides road traffic monitoring, the proposed system can also be used for security surveillance, structural assessment, and industrial processes.