Abstract:
Outdoor air pollution has been found to have a significant adverse effect on health. When the authors attempted to monitor air quality that cyclists or e-scooter users\' breath during commuting in different locations for health and safety analysis, it was found that the existence of internal combustion engine (ICE) cars has a significant effect on the pollution levels and the monitoring process. To comprehensively study the effect of cars and traffic on air quality that cyclists and e-scooters users experience, a low-cost and reliable system was needed to detect the proximity of cars that have diesel or petrol engines. Video cameras can be used to visually detect vehicles, but in the modern age with the existence of many electric and hybrid vehicles and the need to reduce the cost of instrumentation, there was a need to determine the passing of vehicles near e-scooter and bike users from the combined engine and tires sounds. To address this issue, this study suggests a novel approach of using sound waves of internal combustion engines and tire sounds during the passing of cars, combined with AI techniques (neural networks), to detect the proximity of cars from cyclists and e-scooter users. Audio-visual data was collected using Go-Pro cameras in order to combine the data with GPS location and pollution levels. Geographical data maps were produced to demonstrate the density of cars that cyclists encounter when on or near the road. This method will enable air quality monitoring research to detect the existence of ICE cars for future correlation with measured pollution levels. The proposed method allows for:•The automated selection of sensitive features from sound waves to detect vehicles.•Low-cost hardware which is independent of orientation that can be integrated with other air quality and GPS sensors.•The successful application of sensor fusion and neural networks.
摘要:
已发现室外空气污染对健康有重大不利影响。当作者试图监测骑自行车者或电动踏板车使用者在不同地点上下班时呼吸的空气质量,以进行健康和安全分析,研究发现,内燃机(ICE)汽车的存在对污染水平和监测过程有显著影响。为了全面研究汽车和交通对骑车人和电动踏板车用户体验到的空气质量的影响,需要一个低成本和可靠的系统来检测装有柴油或汽油发动机的汽车的接近程度。摄像机可用于视觉检测车辆,但在现代,随着许多电动和混合动力汽车的存在,需要降低仪表成本,有必要从发动机和轮胎的综合声音中确定电动踏板车和自行车使用者附近的车辆通过。为了解决这个问题,这项研究提出了一种在汽车通过过程中使用内燃机声波和轮胎声音的新方法,结合人工智能技术(神经网络),从骑自行车的人和电动踏板车用户检测汽车的接近程度。使用Go-Pro摄像机收集视听数据,以便将数据与GPS位置和污染水平相结合。制作了地理数据地图,以显示骑自行车的人在道路上或附近遇到的汽车密度。这种方法将使空气质量监测研究能够检测ICE汽车的存在,以便将来与测得的污染水平相关。所提出的方法允许:•从声波中自动选择敏感特征以检测车辆。•低成本硬件,独立于可以与其他空气质量和GPS传感器集成的方向。•传感器融合和神经网络的成功应用。