Adapting Public Annotated Data Sets and Low-Quality Dash Cameras for Spatiotemporal Estimation of Traffic-Related Air Pollution: A Transfer-Learning Approach
Publication: Journal of Computing in Civil Engineering
Volume 38, Issue 3
Abstract
This study investigated the utilization of images collected from low-quality dash cameras on passenger vehicles for the estimation of traffic-related air pollution (TRAP). We conducted mobile monitoring along Taiwan Avenue, Taichung, Taiwan, and collected pollution concentration data including carbon dioxide (), nitrogen oxides (), black carbon (BC), and particle number (PN). Dash cameras record images that reveal the environment through which the vehicle passes. Image semantic information such as the proportion of sky, buildings, traffic, and vegetation can be extracted through deep learning models. Training of deep learning models requires the pixel-level labeling of each image, which is labor intensive. We propose the use of publicly available data sets for the training of the deep learning model. Transfer learning was utilized to customize the model for locally collected, unlabeled, low-quality dash camera images. TRAP was estimated with a hybrid model consisting the land-use regression (LUR) and image semantic information. With a five-fold cross-validation, the hybrid model with transfer learning resulted in improved values for (), (), PN (), and BC (). Public labeled data sets and transfer learning may be helpful when labeled data are difficult to acquire in the local region. This work demonstrates the adaptation of image semantic information, extracted from videos captured from vehicle dash cameras, into a LUR model to improve pollutant estimation.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some data used during the study were provided by a third party. Direct requests for these materials may be made to the provider. The Cityscapes data set (Cityscapes 2021) includes data for semantic understanding of urban street scenes.
Acknowledgments
The authors thank The National Research and Technology Council (formerly the Ministry of Science and Technology) of Taiwan for the grant MOST 110-2221-E-002-034-MY3 that has supported this work.
References
Ahn, C. R., P. Lewis, M. Golparvar-Fard, and S. Lee. 2013. “Integrated framework for estimating, benchmarking, and monitoring pollutant emissions of construction operations.” J. Constr. Eng. Manage. 139 (12): A4013003. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000755.
Aldunate, R. G., F. Pena-Mora, and G. E. Robinson. 2005. “Collaborative distributed decision making for large scale disaster relief operations: Drawing analogies from robust natural systems.” Complexity 11 (2): 28–38. https://doi.org/10.1002/cplx.20106.
Alexeeff, S. E., A. Roy, J. Shan, X. Liu, K. Messier, J. S. Apte, C. Portier, S. Sidney, and S. K. Van Den Eeden. 2018. “High-resolution mapping of traffic related air pollution with Google street view cars and incidence of cardiovascular events within neighborhoods in Oakland, CA.” Environ. Health 17 (1): 38. https://doi.org/10.1186/s12940-018-0382-1.
Apte, J. S., K. P. Messier, S. Gani, M. Brauer, T. W. Kirchstetter, M. M. Lunden, J. D. Marshall, C. J. Portier, R. C. Vermeulen, and S. P. Hamburg. 2017. “High-resolution air pollution mapping with Google Street View cars: Exploiting big data.” Environ. Sci. Technol. 51 (Mar): 6999–7008. https://doi.org/10.1021/acs.est.7b00891.
Azar, E., and C. C. Menassa. 2016. “Optimizing the performance of energy-intensive commercial buildings: Occupancy-focused data collection and analysis approach.” J. Comput. Civ. Eng. 30 (5): C4015002. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000521.
Blanco, M. N., A. Gassett, T. Gould, A. Doubleday, D. L. Slager, E. Austin, E. Seto, T. V. Larson, J. D. Marshall, and L. Sheppard. 2022. “Characterization of annual average traffic-related air pollution concentrations in the greater seattle area from a year-long mobile monitoring campaign.” Environ. Sci. Technol. 56 (16): 11460–11472. https://doi.org/10.1021/acs.est.2c01077.
Bowatte, G., C. Lodge, A. J. Lowe, B. Erbas, J. Perret, M. J. Abramson, M. Matheson, and S. C. Dharmage. 2015. “The influence of childhood traffic-related air pollution exposure on asthma, allergy and sensitization: A systematic review and a meta-analysis of birth cohort studies.” Allergy 70 (3): 245–256. https://doi.org/10.1111/all.12561.
Brantley, H. L., G. S. W. Hagler, E. S. Kimbrough, R. W. Williams, S. Mukerjee, and L. M. Neas. 2014. “Mobile air monitoring data-processing strategies and effects on spatial air pollution trends.” Atmos. Meas. Tech. 7 (Mar): 2169–2183. https://doi.org/10.5194/amt-7-2169-2014.
Breiman, L. 1996. “Bagging predictors.” Mach. Learn. 24 (Aug): 123–140. https://doi.org/10.1007/BF00058655.
Brokamp, C., R. Jandarov, M. Hossain, and P. Ryan. 2018. “Predicting daily urban fine particulate matter concentrations using a random forest model.” Environ. Sci. Technol. 52 (7): 4173–4179. https://doi.org/10.1021/acs.est.7b05381.
Brokamp, C., R. Jandarov, M. Rao, G. LeMasters, and P. Ryan. 2017. “Exposure assessment models for elemental components of particulate matter in an urban environment: A comparison of regression and random forest approaches.” Atmos. Environ. 151 (Feb): 1–11. https://doi.org/10.1016/j.atmosenv.2016.11.066.
Chang, T.-H., A. Y. Chen, C.-W. Chang, and C.-H. Chueh. 2014. “Traffic speed estimation through data fusion from heterogeneous sources for first response deployment.” J. Comput. Civ. Eng. 28 (6): 04014018. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000379.
Chen, A. Y., and J. C. Chu. 2016. “TDVRP and BIM integrated approach for in-building emergency rescue routing.” J. Comput. Civ. Eng. 30 (5): C4015003. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000522.
Chen, A. Y., and F. Peña-Mora. 2011. “Decentralized approach considering spatial attributes for equipment utilization in civil engineering disaster response.” J. Comput. Civ. Eng. 25 (6): 457–470. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000100.
Chen, L.-C., G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. 2018. “DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs.” IEEE Trans. Pattern Anal. Mach. Intell. 40 (Mar): 834–848. https://doi.org/10.1109/TPAMI.2017.2699184.
Chen, Y., P. Gu, N. Schulte, X. Zhou, S. Mara, B. E. Croes, J. D. Herner, and A. Vijayan. 2022. “A new mobile monitoring approach to characterize community-scale air pollution patterns and identify local high pollution zones.” Atmos. Environ. 272 (Mar): 118936. https://doi.org/10.1016/j.atmosenv.2022.118936.
Cityscapes. 2021. “The Cityscapes dataset.” Accessed September 30, 2021. https://www.cityscapes-dataset.com/.
Cordts, M., M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. 2016. “The Cityscapes dataset for semantic urban scene understanding.” In Proc., IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). New York: IEEE.
Di, Q., I. Kloog, P. Koutrakis, A. Lyapustin, Y. Wang, and J. Schwartz. 2016. “Assessing exposures with high spatiotemporal resolution across the continental United States.” Environ. Sci. Technol. 50 (May): 4712–4721. https://doi.org/10.1021/acs.est.5b06121.
Eeftens, M., et al. 2012. “Development of land use regression models for , absorbance, , and in 20 European study areas; results of the ESCAPE project.” Environ. Sci. Technol. 46 (Oct): 11195–11205. https://doi.org/10.1021/es301948k.
Friberg, M. D., X. Zhai, H. A. Holmes, H. H. Chang, M. J. Strickland, S. E. Sarnat, P. E. Tolbert, A. G. Russell, and J. A. Mulholland. 2016. “Method for fusing observational data and chemical transport model simulations to estimate spatiotemporally resolved ambient air pollution.” Environ. Sci. Technol. 50 (7): 3695–3705. https://doi.org/10.1021/acs.est.5b05134.
Ganji, A., L. Minet, S. Weichenthal, and M. Hatzopoulou. 2020. “Predicting traffic-related air pollution using feature extraction from built environment images.” Environ. Sci. Technol. 54 (17): 10688–10699. https://doi.org/10.1021/acs.est.0c00412.
Golparvar-Fard, M., and Y. Ham. 2014. “Automated diagnostics and visualization of potential energy performance problems in existing buildings using energy performance augmented reality models.” J. Comput. Civ. Eng. 28 (1): 17–29. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000311.
Hankey, S., and J. D. Marshall. 2015. “Land use regression models of on-road particulate air pollution (particle number, black carbon, , particle size) using mobile monitoring.” Environ. Sci. Technol. 49 (Mar): 9194–9202. https://doi.org/10.1021/acs.est.5b01209.
Hankey, S., P. Sforza, and M. Pierson. 2019. “Using mobile monitoring to develop hourly empirical models of particulate air pollution in a rural Appalachian community.” Environ. Sci. Technol. 53 (Mar): 4305–4315. https://doi.org/10.1021/acs.est.8b05249.
Hatzopoulou, M., M. F. Valois, I. Levy, C. Mihele, G. Lu, S. Bagg, L. Minet, and J. Brook. 2017. “Robustness of land-use regression models developed from mobile air pollutant measurements.” Environ. Sci. Technol. 51 (Mar): 3938–3947. https://doi.org/10.1021/acs.est.7b00366.
Ho, T. K. 1998. “The random subspace method for constructing decision forests.” IEEE Trans. Pattern Anal. Mach. Intell. 20 (Mar): 832–844. https://doi.org/10.1109/34.709601.
Ho, Y.-H., T.-C. Hsiao, and A. Y. Chen. 2023. “Emission analysis of electric motorcycles and assessment of emission reduction with fleet electrification.” IEEE Trans. Intell. Transp. Syst. 24 (12): 15369–15378. https://doi.org/10.1109/TITS.2023.3272385.
Hoek, G., R. M. Krishnan, R. Beelen, A. Peters, B. Ostro, B. Brunekreef, and J. D. Kaufman. 2013. “Long-term air pollution exposure and cardio- respiratory mortality: A review.” Environ. Health 12 (Oct): 43. https://doi.org/10.1186/1476-069X-12-43.
Hopke, P. K., and X. Querol. 2022. “Is improved vehicular NOx control leading to increased urban emissions?” Environ. Sci. Technol. 56 (17): 11926–11927. https://doi.org/10.1021/acs.est.2c04996.
Hu, X., J. H. Belle, X. Meng, A. Wildani, L. A. Waller, M. J. Strickland, and Y. Liu. 2017. “Estimating concentrations in the conterminous United States using the random forest approach.” Environ. Sci. Technol. 51 (Mar): 6936–6944. https://doi.org/10.1021/acs.est.7b01210.
Kelly, F. J., and J. C. Fussell. 2015. “Air pollution and public health: Emerging hazards and improved understanding of risk.” Environ. Geochem. Health 37 (Mar): 631–649. https://doi.org/10.1007/s10653-015-9720-1.
Kerckhoffs, J., J. Khan, G. Hoek, Z. Yuan, T. Ellermann, O. Hertel, M. Ketzel, S. S. Jensen, K. Meliefste, and R. Vermeulen. 2022. “Mixed-effects modeling framework for Amsterdam and Copenhagen for outdoor concentrations using measurements sampled with Google Street View cars.” Environ. Sci. Technol. 56 (11): 7174–7184. https://doi.org/10.1021/acs.est.1c05806.
Larkin, A., J. A. Geddes, R. V. Martin, Q. Xiao, Y. Liu, J. D. Marshall, M. Brauer, and P. Hystad. 2017. “Global land use regression model for nitrogen dioxide air pollution.” Environ. Sci. Technol. 51 (Mar): 6957–6964. https://doi.org/10.1021/acs.est.7b01148.
Larson, T., S. B. Henderson, and M. Brauer. 2009. “Mobile monitoring of particle light absorption coefficient in an urban area as a basis for land use regression.” Environ. Sci. Technol. 43 (3): 4672–4678. https://doi.org/10.1021/es803068e.
Lee, H. J. 2019. “Benefits of high resolution prediction using satellite MAIAC AOD and land use regression for exposure assessment: California examples.” Environ. Sci. Technol. 53 (21): 12774–12783. https://doi.org/10.1021/acs.est.9b03799.
Liu, H.-H., A. Y. Chen, C.-Y. Dai, and W.-Z. Sun. 2015. “Physical infrastructure assessment for emergency medical response.” J. Comput. Civ. Eng. 29 (3): 04014044. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000395.
Liu, X., et al. 2021a. “Spatiotemporal characteristics and driving factors of black carbon in Augsburg, Germany: Combination of mobile monitoring and street view images.” Environ. Sci. Technol. 55 (Nov): 160–168. https://doi.org/10.1021/acs.est.0c04776.
Liu, X., H. Hadiatullah, X. Zhang, L. D. Hill, A. H. A. White, J. Schnelle-Kreis, J. Bendl, G. Jakobi, B. Schloter-Hai, and R. Zimmermann. 2021b. “Analysis of mobile monitoring data from the microAeth® MA200 for measuring changes in black carbon on the roadside in Augsburg.” Atmos. Meas. Tech. 14 (7): 5139–5151. https://doi.org/10.5194/amt-14-5139-2021.
Liu, X., H. Hadiatullah, X. Zhang, J. Schnelle-Kreis, X. Zhang, X. Lin, X. Cao, and R. Zimmermann. 2021c. “Combined land-use and street view image model for estimating black carbon concentrations in urban areas.” Atmos. Environ. 265 (Mar): 118719. https://doi.org/10.1016/j.atmosenv.2021.118719.
Lloyd, M., E. Carter, F. G. Diaz, K. T. Magara-Gomez, K. Y. Hong, J. Baumgartner, V. M. Herrera G, and S. Weichenthal. 2021. “Predicting within-city spatial variations in outdoor ultrafine particle and black carbon concentrations in Bucaramanga, Colombia: A hybrid approach using open-source geographic data and digital images.” Environ. Sci. Technol. 55 (Mar): 12483–12492. https://doi.org/10.1021/acs.est.1c01412.
Messier, K. P., et al. 2018. “Mapping air pollution with Google Street View cars: Efficient approaches with mobile monitoring and land use regression.” Environ. Sci. Technol. 52 (21): 12563–12572. https://doi.org/10.1021/acs.est.8b03395.
Miller, D. J., et al. 2020. “Characterizing elevated urban air pollutant spatial patterns with mobile monitoring in Houston, Texas.” Environ. Sci. Technol. 54 (Nov): 2133–2142. https://doi.org/10.1021/acs.est.9b05523.
Minet, L., R. Liu, M.-F. Valois, J. Xu, S. Weichenthal, and M. Hatzopoulou. 2018. “Development and comparison of air pollution exposure surfaces derived from on-road mobile monitoring and short-term stationary sidewalk measurements.” Environ. Sci. Technol. 52 (6): 3512–3519. https://doi.org/10.1021/acs.est.7b05059.
Morris, B. T., C. Tran, G. Scora, M. M. Trivedi, and M. J. Barth. 2012. “Real-time video-based traffic measurement and visualization system for energy/emissions.” IEEE Trans. Intell. Transp. Syst. 13 (4): 1667–1678. https://doi.org/10.1109/TITS.2012.2208222.
Ohlwein, S., R. Kappeler, M. K. Joss, N. Künzli, and B. Hoffmann. 2019. “Health effects of ultrafine particles: A systematic literature review update of epidemiological evidence.” Int. J. Public Health 64 (Nov): 547–559. https://doi.org/10.1007/s00038-019-01202-7.
OpenStreetMap. 2023. “Map of Taichung, Taiwan.” Accessed August 23, 2023. https://wiki.openstreetmap.org/wiki/Researcher_Information.
Padilla, L. E., et al. 2022. “New methods to derive street-scale spatial patterns of air pollution from mobile monitoring.” Atmos. Environ. 270 (Nov): 118851. https://doi.org/10.1016/j.atmosenv.2021.118851.
Peña-Mora, F., et al. 2010. “Mobile ad hoc network-enabled collaboration framework supporting civil engineering emergency response operations.” J. Comput. Civ. Eng. 24 (3): 302–312. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000033.
Pope, C. A., M. Ezzati, and D. W. Dockery. 2009. “Fine-particulate air pollution and life expectancy in the United States.” N. Engl. J. Med. 360: 376–386. https://doi.org/10.1056/NEJMsa0805646.
Qi, M., K. Dixit, J. D. Marshall, W. Zhang, and S. Hankey. 2022. “National land use regression model for using Street View imagery and satellite observations.” Environ. Sci. Technol. 56 (18): 13499–13509. https://doi.org/10.1021/acs.est.2c03581.
Qi, M., and S. Hankey. 2021. “Using Street View imagery to predict street-level particulate air pollution.” Environ. Sci. Technol. 55 (4): 2695–2704. https://doi.org/10.1021/acs.est.0c05572.
Qiu, W.-X., J.-Y. Han, and A. Y. Chen. 2021. “Measuring in-building spatial-temporal human distribution through monocular image data considering deep learning–Based image depth estimation.” J. Comput. Civ. Eng. 35 (5): 04021014. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000976.
Ramachandra, B., P. Nawathe, J. Monroe, K. Han, Y. Ham, and R. R. Vatsavai. 2018. “Real-time energy audit of built environments: Simultaneous localization and thermal mapping.” J. Infrastruct. Syst. 24 (3): 04018013. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000431.
Reid, C. E., M. Jerrett, M. L. Petersen, G. G. Pfister, P. E. Morefield, I. B. Tager, S. M. Raffuse, and J. R. Balmes. 2015. “Spatiotemporal prediction of fine particulate matter during the 2008 Northern California wildfires using machine learning.” Environ. Sci. Technol. 49 (6): 3887–3896. https://doi.org/10.1021/es505846r.
Rundle, A. G., M. D. Bader, C. A. Richards, K. M. Neckerman, and J. O. Teitler. 2011. “Using Google Street View to audit neighborhood environments.” Am. J. Preventive Med. 40: 94–100. https://doi.org/10.1016/j.amepre.2010.09.034.
Rzotkiewicz, A., A. L. Pearson, B. V. Dougherty, A. Shortridge, and N. Wilson. 2018. “Systematic review of the use of Google Street View in health research: Major themes, strengths, weaknesses and possibilities for future research.” Health Place 52 (Jul): 240–246. https://doi.org/10.1016/j.healthplace.2018.07.001.
Shairsingh, K. K., C. H. Jeong, J. M. Wang, J. R. Brook, and G. J. Evans. 2019. “Urban land use regression models: Can temporal deconvolution of traffic pollution measurements extend the urban lur to suburban areas?” Atmos. Environ. 196 (Jan): 143–151. https://doi.org/10.1016/j.atmosenv.2018.10.013.
Shairsingh, K. K., C.-H. Jeong, J. M. Wang, and G. J. Evans. 2018. “Characterizing the spatial variability of local and background concentration signals for air pollution at the neighbourhood scale.” Atmos. Environ. 183 (Jun): 57–68. https://doi.org/10.1016/j.atmosenv.2018.04.010.
Solomon, P. A., D. Crumpler, J. B. Flanagan, R. Jayanty, E. E. Rickman, and C. E. McDade. 2014. “US National chemical speciation monitoring networks–CSN and IMPROVE: Description of networks.” J. Air Waste Manage. Assoc. 64 (12): 1410–1438. https://doi.org/10.1080/10962247.2014.956904.
Stephan, K., and C. C. Menassa. 2015. “Modeling the effect of building stakeholder interactions on value perception of sustainable retrofits.” J. Comput. Civ. Eng. 29 (4): B4014006. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000409.
Tian, Y., P. deSouza, S. Mora, X. Yao, F. Duarte, L. K. Norford, H. Lin, and C. Ratti. 2022. “Evaluating the meteorological effects on the urban form–air quality relationship using mobile monitoring.” Environ. Sci. Technol. 56 (11): 7328–7336. https://doi.org/10.1021/acs.est.1c04854.
Tripathy, S., B. J. Tunno, D. R. Michanowicz, E. Kinnee, J. L. C. Shmool, S. Gillooly, and J. E. Clougherty. 2019. “Hybrid land use regression modeling for estimating spatio-temporal exposures to , BC, and metal components across a metropolitan area of complex terrain and industrial sources.” Sci. Total Environ. 673 (Jul): 54–63. https://doi.org/10.1016/j.scitotenv.2019.03.453.
Van den Hove, A., J. Verwaeren, J. Van den Bossche, J. Theunis, and B. De Baets. 2020. “Development of a land use regression model for black carbon using mobile monitoring data and its application to pollution-avoiding routing.” Environ. Res. 183 (Apr): 108619. https://doi.org/10.1016/j.envres.2019.108619.
Wood, S. N. 2003. “Thin plate regression splines.” J. R. Stat. Soc. B 65 (Jul): 95–114. https://doi.org/10.1111/1467-9868.00374.
Xu, H., M. J. Bechle, M. Wang, A. A. Szpiro, S. Vedal, Y. Bai, and J. D. Marshall. 2019. “National and exposure models for China based on land use regression, satellite measurements, and universal kriging.” Sci. Total Environ. 655 (Mar): 423–433. https://doi.org/10.1016/j.scitotenv.2018.11.125.
Xu, J., et al. 2022. “Prediction of short-term ultrafine particle exposures using real-time street-level images paired with air quality measurements.” Environ. Sci. Technol. 56 (18): 12886–12897. https://doi.org/10.1021/acs.est.2c03193.
Yuan, Z., J. Kerckhoffs, G. Hoek, and R. Vermeulen. 2022. “A knowledge transfer approach to map long-term concentrations of hyperlocal air pollution from short-term mobile measurements.” Environ. Sci. Technol. 56 (Sep): 13820–13828. https://doi.org/10.1021/acs.est.2c05036.
Zhu, J.-Y., T. Park, P. Isola, and A. A. Efros. 2017. “Unpaired image-to-image translation using cycle-consistent adversarial networks.” In Proc., IEEE Int. Conf. On Computer Vision, 2242–2251. New York: IEEE.
Information & Authors
Information
Published In
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Aug 22, 2023
Accepted: Dec 4, 2023
Published online: Jan 31, 2024
Published in print: May 1, 2024
Discussion open until: Jun 30, 2024
ASCE Technical Topics:
- [Inorganic compounds]
- Air pollution
- Air traffic
- Air transportation
- Artificial intelligence and machine learning
- Business management
- Cameras
- Carbon compounds
- Carbon dioxide
- Chemicals
- Chemistry
- Computer programming
- Computing in civil engineering
- Data collection
- Engineering fundamentals
- Environmental engineering
- Equipment and machinery
- Information management
- Infrastructure
- Management methods
- Methodology (by type)
- Neural networks
- Organic compounds
- Pollution
- Practice and Profession
- Quality control
- Research methods (by type)
- Transportation engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.