چكيده به لاتين
Urban development and the increase in motor vehicles have led to a conflict between traffic supply and demand, ultimately resulting in problems such as traffic congestion, higher accident rates, and pollution. Therefore, identifying and analyzing traffic bottlenecks is crucial for improving the performance of the transportation network. In this study, a novel approach combining map-based data, field measurements, and digital image processing analysis has been used to provide a comprehensive overview of the traffic conditions on the main roads of Isfahan. In the first step, the traffic flow status on six key routes, including four highways and two arterial streets, was monitored over a two-month period (July and August 2024) using traffic images from the Google Maps service. To assess the accuracy of the extracted data, a comparison was made between the queue lengths obtained from image processing and field data collected from three selected intersections in Isfahan. The results of this comparison showed a good correlation in the ten-minute and fifteen-minute time intervals, with the coefficient of determination (R²) ranging from 0.7 to 0.9, indicating a strong correlation between the field data and the results from image processing. Subsequently, by processing the traffic images of these six routes, a total of 16 recurring bottlenecks were identified during the study period. To analyze the impact of these bottlenecks, a bottleneck impact coefficient was used. The results revealed that the bottlenecks located on Kharazi Highway, with an impact coefficient of 351 km·hour, had the highest contribution to traffic congestion during working days. These points can be considered as priority options for infrastructure and management improvement planning. Overall, the findings of this study suggest that Google Maps traffic data, as a secondary and cost-effective source, can serve as a suitable alternative to traditional data sources such as inductive loop detectors. The use of this information source not only reduces data collection costs but also enables continuous monitoring, trend analysis, and facilitates decision-making in urban transportation planning.
