Self-Updating Vehicle Monitoring Framework Employing Distributed Acoustic Sensing towards Real-World Settings

TL;DR

This paper presents a real-time semi-supervised vehicle monitoring framework using Distributed Acoustic Sensing data, which adapts autonomously, requires minimal manual labels, and outperforms existing models in accuracy and robustness.

Contribution

The study introduces a novel semi-supervised, self-updating vehicle monitoring framework that leverages DAS data, a prior shape loss, and minimal manual labels for improved urban vehicle detection.

Findings

Outperformed YOLO in accuracy with only 35 labeled images

Achieved 18% higher mAP than Efficient Teacher

Demonstrated effective autonomous model adaptation

Abstract

The recent emergence of Distributed Acoustic Sensing (DAS) technology has facilitated the effective capture of traffic-induced seismic data. The traffic-induced seismic wave is a prominent contributor to urban vibrations and contain crucial information to advance urban exploration and governance. However, identifying vehicular movements within massive noisy data poses a significant challenge. In this study, we introduce a real-time semi-supervised vehicle monitoring framework tailored to urban settings. It requires only a small fraction of manual labels for initial training and exploits unlabeled data for model improvement. Additionally, the framework can autonomously adapt to newly collected unlabeled data. Before DAS data undergo object detection as two-dimensional images to preserve spatial information, we leveraged comprehensive one-dimensional signal preprocessing to mitigate noise. Furthermore, we propose a novel prior loss that incorporates the shapes of vehicular traces to track a single vehicle with varying speeds. To evaluate our model, we conducted experiments with seismic data from the Stanford 2 DAS Array. The results showed that our model outperformed the baseline model Efficient Teacher and its supervised counterpart, YOLO (You Only Look Once), in both accuracy and robustness. With only 35 labeled images, our model surpassed YOLO's mAP 0.5:0.95 criterion by 18% and showed a 7% increase over Efficient Teacher. We conducted comparative experiments with multiple update strategies for self-updating and identified an optimal approach. This approach surpasses the performance of non-overfitting training conducted with all data in a single pass.