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

Traffic emission is one of the major contributors to urban PM, an important environmental health hazard. Estimating roadside PM concentration increments (above background levels) due to vehicles would assist in understanding pedestrians' actual exposures. This work combines PM sensing and vehicle detecting to acquire roadside PM 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 PM sensors installed at two roadside locations with vehicle counts from the nearby governmental cameras analyzed by YOLOv3-tiny-3l, roadside PM concentration increments due to on-road sedans were estimated to be 0.0027-0.0050 µg/m. This practical and low-cost method can be further applied in other countries to assess the impacts of vehicles on roadside PM concentrations.