<![CDATA[Traffic congestion in urban areas has become a crucial issue, impacting time efficiency, energy consumption, and quality of life. One of the main causes of difficulties in traffic management is the lack of optimal predictive systems capable of detecting and adaptively responding to vehicle movement patterns. This study proposes a historical digital image-based approach to extract traffic movement patterns and density based on vehicle type and dimensions. The developed model utilizes historical traffic video footage from CCTV systems as a visual data source, which is then processed using the YOLOv5 algorithm to detect the number, size, and type of vehicles. After the detection process, vehicle information is converted into a sequential format that reflects vehicle movement in the temporal dimension. This data is then analyzed using a Long Short-Term Memory (LSTM) model to generate traffic density prediction patterns. This study also compares the performance of LSTM with other algorithms such as Random Forest and XGBoost in terms of prediction accuracy. Model evaluation is conducted using MSE and RMSE metrics to measure accuracy against actual data.The research results show that the integration of dimension-based vehicle detection with a visual historical data-driven prediction approach can improve the accuracy and flexibility of modeling future traffic conditions. This approach significantly contributes to the development of intelligent transportation systems that can adapt to dynamic environmental conditions and traffic patterns]]>
Copyrights © 2025
