Fusion of Environmental Sensing on PM_2.5 and Deep Learning on Vehicle Detecting for Acquiring Roadside PM_2.5 Concentration Increments

Abstract

Traffic emission is one of the major contributors to urban PM2.5, an important environmental health hazard. Estimating roadside PM2.5 concentration increments (above background levels) due to vehicles would assist in understanding pedestrians’ actual exposures. This work combines PM2.5 sensing and vehicle detecting to acquire roadside PM2.5 concentration increments due to vehicles. An automatic traffic analysis system (YOLOv3-tiny-3l) was applied to simultaneously detect and track vehicles with deep learning and traditional optical flow techniques, respectively, from governmental cameras that have low resolutions of only 352 × 240 pixels. Evaluation with 20% of the 2439 manually labeled images from 23 cameras showed that this system has 87% and 84% of the precision and recall rates, respectively, for five types of vehicles, namely, sedan, motorcycle, bus, truck, and trailer. By fusing the research-grade observations from PM2.5 sensors installed at two roadside locations with vehicle counts from the nearby governmental cameras analyzed by YOLOv3-tiny-3l, roadside PM2.5 concentration increments due to on-road sedans were estimated to be 0.0027–0.0050 µg/m3. This practical and low-cost method can be further applied in other countries to assess the impacts of vehicles on roadside PM2.5 concentrations.

Keywords

• air pollution sensing
• low-cost sensor
• particle source
• transportation emission
• vehicle counting
• vehicle classification