Traffic Signal Controll by Tracking, counting and speed estimation of vehicles on surveillance cameras using YOLO v9 and Reinforcement Learning

This repository contains Python code for tracking vehicles (such as cars, buses, and bikes) as they enter and exit the road, thereby incrementing the counters for incoming and outgoing vehicles. and also speed estimation is calculated by mathematical calcualtion and video info like fps

And also custom OpenAI gym envornment and Rainbow agent to train a RL model based on traffic state reaciving from surveillance cameras

article link: https://www.researchgate.net/publication/380820559_Traffic_control_using_intelligent_timing_of_traffic_lights_with_reinforcement_learning_technique_and_real-time_processing_of_surveillance_camera_images

Installation

1. git clone https://github.com/Mahdijamebozorg/Traffic-Signal_Control-with-RL-YOLOv9-Surveillance-Camera.git
2. pip install ultralytics
3. pip install supervision
4. pip install gym
5. pip insatll tensorflow
6. pip install torch
...

CompressedTrafficLightObjectTracking.mp4

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.