Estimating urban noise along road network from street view imagery

Abstract

Estimating road traffic noise is essential for examining the quality of sounding environment and mitigating such a non-negligible pollutant in urban areas. However, existing estimated models often have limited applicability to specific traffic conditions, while the required parameters may not be readily available for city-wide collection. This paper proposes a data-driven approach for measuring road-level acoustic information of traffic with street view imagery. Specifically, we utilize portable vehicle-equipped hardware for in-situ noise acquisition and employ a deep learning model ResNet to learn high-level visual features from street view images that are closely associated with road traffic noise. The ResNet captures meaningful patterns from the input data, and the output probability vectors are then fed into a Random-Forest regression algorithm to quantitatively estimate the noise in decibels for different road segments. The MAE and RMSE of the DCNN-RF model are 2.01 and 2.71, respectively. Additionally, we employ a gradient-weighted Class Active Mapping approach to visually interpret our deep learning model and explore the significant elements in streetscapes that contribute to the model's estimations. Our proposed framework facilitates low-cost and fine-scale road traffic noise estimations and sheds light on how auditory information could be inferred from street imagery, which may benefit practices in geography and urban planning.

Keywords:

• Road traffic noise
• street view imagery
• deep learning
• build environment
• urban planning

Acknowledgment

The authors would like to thank Urli for the valuable advice provided during the initial stages of the experiment and Mr. Mengze Gao for designing and 3D-printing the enclosure for the data acquisition device. Thanks to the financial support from the National Natural Science Foundation of China [42271476]; the Wuhan University 351 Talent Program, 2020; the State Key Laboratory of Resources and Environmental Information System [2023OPEN007] and the Guangdong Science and Technology Strategic Innovation Fund [2020B1212030009].

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The original in-situ road traffic noise data with geographic coordinates collected by the experimental vehicle using our portable device, as well as the road traffic noise estimation model and some sample street view images used for demonstration are available at https://github.com/kellyhuang313/traffic-noise-estimation. Instructions for executing the code are provided in the README.txt.

Notes

1 https://www.openstreetmap.org/

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [42271476]; the Wuhan University 351 Talent Program, 2020; and the Guangdong Science and Technology Strategic Innovation Fund [2020B1212030009]. This work was also supported by State Key Laboratory of Resources and Environmental Information System [2023OPEN007].

Notes on contributors

Jing Huang

Jing Huang is a Master’s student at the School of Resource and Environment Sciences, Wuhan University, China. Her research focuses on the analysis of spatio-temporal data in urban geography. Her contributions to the paper include developing traffic noise estimation model, algorithm implementation, conducting case studies, and manuscript writing of this paper.

Teng Fei

Teng Fei is an Associate Professor of Cartography and GIScience at the School of Resources and Environment Science, Wuhan University, specializing in the study of urban geographic big data and ecological remote sensing. He contributed to the ideation, conceptualizing, the design of a portable device for in-situ traffic noise data acquisition and manuscript revision.

Yuhao Kang

Yuhao Kang is an assistant professor in GIScience directing the GISense Lab at the Department of Geography, University of South Carolina. His research interests include Human-centered Geospatial Data Science, GIScience, GeoAI, and Urban Visual Intelligence. He contributed to the development of the methodology, as well as the review and editing of this manuscript.

Jun Li

Jun Li graduated from the School of Resource and Environment Sciences, Wuhan University, China. His research is oriented toward geospatial analysis. He contributed to the data processing of street view imagery and traffic noise data.

Ziyu Liu

Ziyu Liu graduated from the School of Resource and Environment Sciences, Wuhan University, China. Her recent work focuses on the use of accurate road PV production estimation from street view image. She contributed to the data collection and curation of the street view images in this work.

Guofeng Wu

Guofeng Wu is a Professor at the Department of Urban Informatics, Shenzhen University, China. His research focuses on the application of remote sensing to natural resources and ecological environments. He is co-responsible for the presentation of this paper.