Traffic Signal Timing Optimization Model Based on Video Surveillance Data and Snake Optimization Algorithm.

Area of Science:

• Intelligent Transportation Systems
• Urban Planning
• Computer Vision
• Machine Learning

Background:

• Rapid urban growth exacerbates traffic congestion and environmental pollution.
• Effective urban traffic management relies heavily on signal timing optimization.
• Existing methods may not adequately address dynamic traffic conditions.

Purpose of the Study:

• To propose a VISSIM simulation-based traffic signal timing optimization model.
• To address urban traffic congestion issues caused by dynamic traffic flow.
• To enhance the efficiency of urban traffic management systems.

Main Methods:

• Utilized YOLO-X for road information extraction from video surveillance.
• Employed Long Short-Term Memory (LSTM) for future traffic flow prediction.
• Optimized the model using the Snake Optimization (SO) algorithm.
• Validated the model through an empirical example using VISSIM simulation.

Main Results:

• The proposed model provides an improved signal timing scheme compared to fixed timing.
• Demonstrated a significant decrease of 23.34% in traffic congestion within the observed period.
• The VISSIM simulation confirmed the model's effectiveness in real-world scenarios.

Conclusions:

• The developed model offers a feasible and effective approach for traffic signal timing optimization.
• The integration of AI models enhances predictive capabilities for traffic flow.
• This research contributes to alleviating urban traffic congestion and improving traffic management.