Spatio-temporal patterns of traffic-related air pollutant emissions in different urban functional zones estimated by real-time video and deep learning technique
(2019) In Journal of Cleaner Production 238.- Abstract
The aim of this paper is to explore the relationship between spatial-temporal patterns of vehicles types and numbers in different urban functional zones and traffic-related air pollutant emissions with real-time traffic data collected from traffic surveillance video and image recognition. The data were analyzed by using video-based detection technique, while the air pollution was quantified via pollutant emission coefficients. The results revealed that: (1) the order of traffic-related pollutant emissions was expressway > business zone > industrial zone > residential zone > port; (2) daily maximum emissions of each pollutant occurred in different functional zones on weekdays and weekends. With the exception of expressway,... (More)
The aim of this paper is to explore the relationship between spatial-temporal patterns of vehicles types and numbers in different urban functional zones and traffic-related air pollutant emissions with real-time traffic data collected from traffic surveillance video and image recognition. The data were analyzed by using video-based detection technique, while the air pollution was quantified via pollutant emission coefficients. The results revealed that: (1) the order of traffic-related pollutant emissions was expressway > business zone > industrial zone > residential zone > port; (2) daily maximum emissions of each pollutant occurred in different functional zones on weekdays and weekends. With the exception of expressway, the business zones had the highest emissions of CO, HC and VOC on weekdays, while the highest emissions of all the pollutants (CO, HC, NOx, PM2.5, PM1.0, and VOC) were at the weekend. The industrial zone had the highest emissions of NOx, PM2.5 and PM1.0 on weekdays; (3) pollutant emissions (CO, HC, NOx, PM2.5, PM1.0 and VOC) in all functional zones peaked in the morning and evening peak except at port sites; (4) cars and motorcycles represented the major source of traffic-related pollutant emissions. Collecting data through video-based vehicle detection with finer spatio-temporal resolution represents a cost-effective way of mapping spatio-temporal patterns of traffic-related air pollution to contribute to urban planning and climate change studies.
(Less)
- author
- Song, Jinchao ; Zhao, Chunli LU ; Lin, Tao ; Li, X. and Prishchepov, Alexander V.
- organization
- publishing date
- 2019
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Deep learning, Pollutant emissions, Urban functional zones, Video-based vehicle detection
- in
- Journal of Cleaner Production
- volume
- 238
- article number
- 117881
- publisher
- Elsevier
- external identifiers
-
- scopus:85070507232
- ISSN
- 0959-6526
- DOI
- 10.1016/j.jclepro.2019.117881
- language
- English
- LU publication?
- yes
- id
- fd1dec38-ba0e-4462-b7c7-09dd341bbc38
- date added to LUP
- 2019-08-29 12:58:17
- date last changed
- 2022-04-26 03:47:17
@article{fd1dec38-ba0e-4462-b7c7-09dd341bbc38,
abstract = {{<p>The aim of this paper is to explore the relationship between spatial-temporal patterns of vehicles types and numbers in different urban functional zones and traffic-related air pollutant emissions with real-time traffic data collected from traffic surveillance video and image recognition. The data were analyzed by using video-based detection technique, while the air pollution was quantified via pollutant emission coefficients. The results revealed that: (1) the order of traffic-related pollutant emissions was expressway > business zone > industrial zone > residential zone > port; (2) daily maximum emissions of each pollutant occurred in different functional zones on weekdays and weekends. With the exception of expressway, the business zones had the highest emissions of CO, HC and VOC on weekdays, while the highest emissions of all the pollutants (CO, HC, NOx, PM2.5, PM1.0, and VOC) were at the weekend. The industrial zone had the highest emissions of NOx, PM2.5 and PM1.0 on weekdays; (3) pollutant emissions (CO, HC, NOx, PM2.5, PM1.0 and VOC) in all functional zones peaked in the morning and evening peak except at port sites; (4) cars and motorcycles represented the major source of traffic-related pollutant emissions. Collecting data through video-based vehicle detection with finer spatio-temporal resolution represents a cost-effective way of mapping spatio-temporal patterns of traffic-related air pollution to contribute to urban planning and climate change studies.</p>}},
author = {{Song, Jinchao and Zhao, Chunli and Lin, Tao and Li, X. and Prishchepov, Alexander V.}},
issn = {{0959-6526}},
keywords = {{Deep learning; Pollutant emissions; Urban functional zones; Video-based vehicle detection}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Journal of Cleaner Production}},
title = {{Spatio-temporal patterns of traffic-related air pollutant emissions in different urban functional zones estimated by real-time video and deep learning technique}},
url = {{http://dx.doi.org/10.1016/j.jclepro.2019.117881}},
doi = {{10.1016/j.jclepro.2019.117881}},
volume = {{238}},
year = {{2019}},
}