标题: Listen to the road: acoustic traffic monitoring on edge platforms via Lightweight Noise Spectrogram Transformer (LNST)
作者: Guowen Li (李国稳 硕士); Zihang Huang (黄梓航 硕士 *); Teng Fei (费腾); Dunxin Jia; Meng Bian
来源出版物: Pervasive and Mobile Computing 卷: 115 页: 102132 DOI: 10.1016/j.pmcj.2025.102132 Published Date: 2026-01-01
摘要: Accurate real-time traffic flow monitoring is crucial for intelligent transportation systems (ITS), enabling optimized traffic management, urban planning, and policy-making. However, conventional methods face cost, deployment, weather, and privacy challenges. Addressing these shortcomings, this study investigates the potential of utilizing ubiquitous traffic noise, an inherently accessible, cost-efficient, non-intrusive, and privacy-preserving signal, as a viable data source. We propose the Lightweight Noise Spectrogram Transformer (LNST), a novel deep learning model for analyzing traffic noise spectrograms as a Proof of Concept. LNST leverages the Transformer architecture's self-attention mechanism to effectively capture long-range temporal and spectral dependencies crucial for interpreting complex traffic acoustics. Trained and evaluated on diverse urban traffic scenarios, LNST demonstrates significant advantages. Experimental results show it consistently outperforms baseline models, achieving superior prediction accuracy (MSE, MAE, R²). Furthermore, through transfer learning and model pruning, LNST achieves high computational efficiency with substantially fewer parameters and faster inference speeds. Its lighter design also ensures its feasibility for deployment on resource-constrained edge computing platforms. This work validates the practicality of acoustic sensing for traffic monitoring and presents an accurate, computationally efficient, and LNST as a cost-effective, easily deployable, and privacy-respecting solution, offering a valuable supplementary tool for advancing ITS.
作者关键词: Edge computing; Intelligent transportation system; Traffic flow monitoring; Traffic noise; Transformer
KeyWords Plus:
地址: [Guowen Li, Zihang Huang, Teng Fei] School of Resource and Environmental Sciences, Wuhan University, Wuhan, 430079, China
[Teng Fei] School of Forestry, University of Canterbury, Christchurch, 8140, New Zealand
[Dunxin Jia] China Academy of Urban Planning and Design, Western Branch, Chongqing, 401121, China
[Meng Bian] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, 430079, China
通讯作者地址: Zihang Huang(通讯作者) School of Resource and Environmental Sciences, Wuhan University, Wuhan, 430079, China
电子邮件地址:
[email protected]影响因子： 3.5
