Description

AI Traffic Jam Optimizer

Smart Traffic Management – IoT & AI Prototype for Real-Time Traffic Monitoring
General Description
This project aims to develop a Smart City prototype for real-time traffic monitoring and analysis at a selected key intersection in Holon.
The system will use computer vision and artificial intelligence to analyze traffic conditions from regular video cameras or recorded video. The system will detect, classify, track, and count vehicles in real time and transmit the collected traffic data to a central server.
The project combines Artificial Intelligence, Computer Vision, IoT, and long-range wireless communication to create a real-time traffic monitoring solution that can provide a dynamic view of traffic conditions at the selected intersection.
Project Scope
The project focuses on developing an end-to-end prototype for monitoring traffic at one selected intersection.
The system will be built using three main layers:
•	AI & Computer Vision Layer: Processing video using Python, OpenCV, and AI models such as YOLO for vehicle detection, classification, counting, and object tracking.
•	Network Layer: Packaging the extracted traffic data into an optimized byte array and transmitting it over LoRaWAN to a municipal gateway.
•	Application Layer: A central Python server using Flask or FastAPI will receive and decode the data, store the information, and provide a dynamic GIS-based dashboard displaying the traffic level at the intersection in real time.
The project will be developed through four 30-day sprints:
Sprint 1 – Research, Architecture and Data Collection
•	Define the system architecture.
•	Set up a shared GitHub repository and Git workflow.
•	Acquire the required hardware, including a microcontroller and LoRa transmitter.
•	Obtain video footage or set up a simple camera at the selected intersection.
•	Prepare the dataset for development.
Sprint 2 – AI Model and Vehicle Detection
•	Develop Python code using OpenCV and YOLO.
•	Detect, classify, and count vehicles such as cars, trucks, and motorcycles.
•	Calibrate object-tracking mechanisms to prevent duplicate counting.
•	Develop the initial backend structure.
Sprint 3 – Communication and Data Packaging
•	Implement serialization and packaging of traffic measurements into byte arrays.
•	Connect the system to the gateway.
•	Transmit data successfully over the LoRa network.
•	Implement an MQTT listener on the server side.
Sprint 4 – Integration, Dashboard and Final Deliverables
•	Decode incoming data on the server.
•	Update the database with the received traffic information.
•	Develop a dynamic map-based frontend dashboard.
•	Perform end-to-end testing.
•	Finalize and document the source code in GitHub.
•	Prepare the project presentation, academic poster, and demonstration video.
Student Requirements
•	Teamwork
•	Full participation in weekly meetings
•	High motivation and commitment
•	Independent learning
•	Personal responsibility
•	Ability to work with Python and modern software development technologies
•	Interest in Artificial Intelligence, Computer Vision, and IoT
Development Tools
•	Python
•	OpenCV
•	YOLO
•	Computer Vision and Object Tracking
•	Flask / FastAPI
•	MQTT
•	LoRaWAN
•	Python struct library
•	GitHub / Git
•	GIS / Dynamic Map Technologies
•	Microcontroller and LoRa hardware
Deliverables
•	Working Prototype: An end-to-end system demonstrating AI-based video processing, traffic data extraction, LoRa transmission, and real-time updates to the municipal control dashboard.
•	GitHub Repository: Complete, documented, and organized source code, including project documentation.
•	Project Presentation: A comprehensive technological and business presentation covering the system architecture, selected AI model, development challenges, and results.
•	Academic Poster: A visual poster presenting system diagrams, AI model accuracy graphs, and dashboard screenshots.
•	YouTube Demonstration Video: A short 4–5 minute video including a technical explanation and live demonstration of the system and AI model.
Additional Notes
This project is part of a Smart City initiative and is designed as a student-developed prototype for traffic monitoring in Holon.
The scope of the project is intentionally limited to one selected intersection, allowing students to develop and demonstrate a complete end-to-end solution.
The project may support future collaboration with the municipality and serve as a foundation for expanding the system to additional intersections and traffic-management scenarios.
AI Traffic Jam Optimizer

AI and Machine Learning

Description

Emphasis in project execution

The project is has cooperation with the industry and combines meeting deadlines while being creative and focused on the task

THE PROJECT IS AT FULL CAPACITY
