THE USE OF VIDEO SURVEILLANCE SYSTEMS FOR MONITORING THE IMPACT OF MOTOR VEHICLES ON AIR QUALITY

The purpose of the study is to develop and implement an air quality monitoring system in urban areas using video surveillance and recording to assess the impact of motor vehicles on atmospheric air.This approach enhances the accuracy of monitoring pollutant concentrations and optimizes traffic flows to reduce emissions of harmful substances.Air pollution from motor vehicles is one of the most pressing environmental issues in modern cities, especially in densely populated urban areas such as Kryvyi Rih.Therefore, the implementation of new monitoring systems is relevant for improving air quality and reducing environmental risks to public health.The study employs a comprehensive approach that includes data collection through video surveillance, analysis of traffic intensity, classification of vehicles by type and fuel, and modeling pollutant dispersion considering meteorological conditions.The collected data were processed using machine learning methods to develop air quality models.Video surveillance allows for real-time analysis of traffic flow dynamics, identification of areas with high pollutant concentrations, and prompt response to changes in traffic intensity.Additionally, video analytics can accurately determine vehicle types, speeds, and movement directions, enabling a more accurate assessment of the impact of different categories of vehicles on air quality.The study results showed that the proposed system enables the creation of detailed maps of daily and weekly traffic patterns, identification of areas with high pollutant concentrations, and optimization of traffic flows by redirecting vehicles to less congested areas.This contributes to the reduction of nitrogen dioxide (NO), carbon monoxide (CO), and particulate matter emissions in the most polluted areas.Moreover, the system has proven effective in organizing modern parking systems, reducing traffic congestion, and improving traffic management.The scientific novelty of the study lies in the proposed approach to air quality monitoring using video surveillance data to assess the impact of traffic flows on atmospheric pollution.The application of machine learning methods for analyzing traffic data improves the accuracy of forecasting air quality changes depending on traffic intensity and meteorological conditions.The practical significance of the study lies in the possibility of integrating the system into urban information platforms and environmental monitoring services, allowing for the prompt detection of air pollution norm exceedances and the implementation of effective management decisions.This also contributes to optimizing traffic flows, improving traffic management, and reducing environmental health risks.