This project involves utilizing both the YOLOv8 and YOLOv5 models to analyze vehicle counts on the road. By leveraging the strengths of both models, we aim to evaluate their performances in real-time vehicle detection and ensure the highest accuracy and efficiency. Additionally, we are manipulating the time counter using an algorithm that efficiently changes the traffic lights to minimize the standing time for approaching vehicles. This optimization has been simulated using Pygame.
YOLOv8 is a state-of-the-art object detection model known for its high accuracy. We have implemented YOLOv8 to detect and count vehicles on the road in real-time.
YOLOv5 is another powerful object detection model, but with a focus on speed and efficiency. It is particularly practical due to its ease of use on small devices like Raspberry Pi, making it ideal for embedded systems and real-time applications.
- Real-time Vehicle Detection: Using YOLOv8 and YOLOv5 models for accurate vehicle counting.
- Performance Comparison: Evaluating the performance of both models to determine the best fit for different applications.
- Embedded Systems: YOLOv5's compatibility with small devices like Raspberry Pi for practical, real-world implementations.
The future potential of this project is immense. We have developed an algorithm to adjust traffic lights based on real-time vehicle data, aiming to integrate this algorithm into a real-time detection system using Raspberry Pi and a traffic light model with cameras. This integration will help reduce congestion and enhance traffic flow, making our cities smarter.
- Machine Learning
- AI
- Traffic Management
- YOLOv8
- YOLOv5
- Deep Learning
- Hugging Face
Thank you for checking out our project! We are excited about the possibilities and the positive impact it can have on urban traffic management.