Advanced road traffic monitoring with distributed acoustic sensing and deep learning

Urban traffic management poses a significant challenge for cities worldwide, intensified by the growing number of vehicles on road infrastructures. Traditional methods, such as cameras and loop detectors, are often suboptimal due to their high deployment and maintenance costs, limited sensing resolution, and privacy concerns. Recently, Distributed Acoustic Sensing (DAS) technology has emerged as a promising solution for traffic monitoring. By transforming standard fiber-optic telecommunication cables into an array of vibration sensors, DAS captures vehicle-induced subsurface deformation with high spatio-temporal resolution, providing a cost-effective and privacy-preserving alternative.In this thesis, we propose several models and frameworks for comprehensive traffic monitoring using DAS technology, focusing on four key aspects: vehicle detection, speed estimation, counting, and classification. First, we introduce a self-supervised DAS data alignment model that temporally aligns the recorded DAS data across multiple measurement points, enabling the extraction of the traffic information. Our model integrates a deep learning module with a non-uniform time warping block, making it capable of handling challenging traffic conditions and accurately aligning DAS data.Next, we present a vehicle detection and speed estimation framework built on the alignment model. Vehicle detection is formulated within the Generalized Likelihood Ratio Test (GLRT) framework, allowing for reliable detection and localization of vehicles. Speed estimation is achieved over the detected vehicles using the warps from the alignment model, and the results are validated against dedicated sensors. Our method achieves a mean error of less than kmph{3}, outperforming traditional time series alignment methods like Dynamic Time Warping (DTW) by nearly 80%. Furthermore, our model's computing time is 16 times faster than DTW, enabling real-time performance.Lastly, we introduce new vehicle counting and classification methods that leverage the DAS technology. We present a first solution, based solely on vehicle detection results, which is effective for truck counting but shows limitations in cars counting under high-traffic conditions. To address these limitations, we develop a second approach for vehicle counting using a supervised deep learning model trained on a specific road section, using the vehicle counting results of the first method and low-time-resolution labels from dedicated sensors. Through an optimal transport-based feature mapping technique, we extend the model to other road segments, demonstrating its scalability and adaptability. Using the first truck counting method along with the deep learning-based vehicle counting model results in a comprehensive vehicle counting and classification solution.Overall, this thesis presents a robust and scalable framework for road traffic monitoring using DAS technology, delivering both high accuracy and real-time performance. The framework paves the way for extracting a wide range of other crucial traffic information, such as accident detection. Moreover, this approach can be generalized to various road configurations and extended to other transportation modes, such as tramways and trains, demonstrating its broader applicability.