Liu Yanming, Zhang Yuxi, Yu Pei, Ye Tingting, Zhang Yiwen, Xu Rongbin, Li Shanshan, Guo Yuming
School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3004, Australia.
School of Public Health and Preventive Medicine, Monash University, Melbourne, VIC 3004, Australia; School of Life and Environmental Sciences, the University of Sydney, Sydney, NSW 2006, Australia.
Sci Total Environ. 2024 Feb 20;912:169233. doi: 10.1016/j.scitotenv.2023.169233. Epub 2023 Dec 12.
Air pollution has caused a significant burden in terms of mortality and mobility worldwide. However, the current coverage of air quality monitoring networks is still limited.
This study aims to apply a novel approach to convert the existing traffic cameras into sensors measuring particulate matter with a diameter of 2.5 μm or less (PM) so that the coverage of PM monitoring could be expanded without extra cost.
In our study, the traffic camera images were collected at a rate of 4 images/h and the corresponding hourly PM concentration was collected from the reference grade PM station 3 km away. A customized neural network model was trained to obtain the PM concentration from images followed by a random forest model to predict the hourly PM concentration. The saliency maps and the feature importance were utilized to interpret the neural network.
Proposed novel approach has a high prediction performance to predict hourly PM from traffic camera images, with a root mean square error (RMSE) of 0.76 μg/m and a coefficient of determination (R) of 0.98. The saliency map shows neural network focuses on unobstructed far-end road surfaces while the random forest feature importance highlights the first quarter image's significance. The model performance is robust whether weather conditions are controlled or not.
Our study provided a practical approach to converting the existing traffic cameras into PM sensors. The deep learning method based on the Resnet architecture in our study can broaden the coverage of PM monitoring with no additional infrastructure needed.
空气污染在全球范围内已造成了巨大的死亡和交通负担。然而，目前空气质量监测网络的覆盖范围仍然有限。
本研究旨在应用一种新方法，将现有的交通摄像头转换为测量直径小于等于2.5微米颗粒物（PM）的传感器，从而在无需额外成本的情况下扩大PM监测的覆盖范围。
在我们的研究中，以每小时4张图像的速率收集交通摄像头图像，并从3公里外的参考级PM监测站收集相应的每小时PM浓度。训练一个定制的神经网络模型从图像中获取PM浓度，随后使用随机森林模型预测每小时的PM浓度。利用显著性图和特征重要性来解释神经网络。
所提出的新方法在从交通摄像头图像预测每小时PM方面具有很高的预测性能，均方根误差（RMSE）为0.76微克/立方米，决定系数（R）为0.98。显著性图显示神经网络关注无遮挡的远端路面，而随机森林特征重要性突出了第一季度图像的重要性。无论是否控制天气条件，模型性能都很稳健。
我们的研究提供了一种将现有交通摄像头转换为PM传感器的实用方法。我们研究中基于Resnet架构的深度学习方法可以在无需额外基础设施的情况下扩大PM监测的覆盖范围。
