Integrating Vehicle Acoustic Data for Enhanced Urban Traffic Management: A Study on Speed Classification in Suzhou

2025-06-26

AI Summary

To address the challenge of real-time vehicle speed classification in urban traffic management, this paper proposes an acoustic-signal-based speed classification method. We introduce SZUR-Acoustic—the first open-source, rigorously annotated, and protocol-compliant acoustic dataset collected from Chinese urban roads. We design a bimodal convolutional neural network (BMCNN) featuring a novel cross-modal attention mechanism that jointly models MFCCs and wavelet packet energy features. Additionally, we incorporate adaptive denoising and normalization in preprocessing. Our method achieves 87.56% accuracy on SZUR-Acoustic and 96.28% on the benchmark IDMT-Traffic dataset; ablation studies confirm the efficacy of each component. The proposed approach advances real-time intelligent traffic control and noise mitigation in smart cities, significantly improving model robustness and cross-scenario generalization capability.

Technology Category

• Machine Learning: Multimodal Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This study presents and publicly releases the Suzhou Urban Road Acoustic Dataset (SZUR-Acoustic Dataset), which is accompanied by comprehensive data-acquisition protocols and annotation guidelines to ensure transparency and reproducibility of the experimental workflow. To model the coupling between vehicular noise and driving speed, we propose a bimodal-feature-fusion deep convolutional neural network (BMCNN). During preprocessing, an adaptive denoising and normalization strategy is applied to suppress environmental background interference; in the network architecture, parallel branches extract Mel-frequency cepstral coefficients (MFCCs) and wavelet-packet energy features, which are subsequently fused via a cross-modal attention mechanism in the intermediate feature space to fully exploit time-frequency information. Experimental results demonstrate that BMCNN achieves a classification accuracy of 87.56% on the SZUR-Acoustic Dataset and 96.28% on the public IDMT-Traffic dataset. Ablation studies and robustness tests on the Suzhou dataset further validate the contributions of each module to performance improvement and overfitting mitigation. The proposed acoustics-based speed classification method can be integrated into smart-city traffic management systems for real-time noise monitoring and speed estimation, thereby optimizing traffic flow control, reducing roadside noise pollution, and supporting sustainable urban planning.

Problem

• Classify vehicle speed using urban road acoustic data
• Develop bimodal CNN for noise-speed coupling analysis
• Enhance traffic management via real-time noise monitoring

Innovation

• Bimodal-feature-fusion CNN for speed classification
• Adaptive denoising and normalization preprocessing
• Cross-modal attention for time-frequency feature fusion