Automation is one of the most widely used concepts in the field of electronics and modern technology. The increasing demand for automation has brought many advancements and innovations in existing systems. Automated monitoring systems are widely used today for improving safety, security, and efficiency in transportation. This project focuses on designing a surveillance system for bike riders using a Raspberry Pi 3A+ processor and Pi Camera. The Raspberry Pi acts as the main processing unit or the heart of the system. The system uses Convolutional Neural Network (CNN) based Machine Learning algorithms along with OpenCV image processing techniques to monitor traffic violations. The Pi Camera continuously captures live video or images of bike riders. The captured images are processed by the Raspberry Pi using the trained machine learning model to detect violations such as riding without a helmet, triple riding (three persons on a bike), and wrong-side driving. When any violation is detected, the information is displayed on an LCD module connected to the Raspberry Pi. Additionally, the system captures the image of the violating rider and automatically sends the captured image through email as evidence along with Buzzer. This automated monitoring system helps traffic authorities identify rule violations efficiently and improves road safety. Thus, the proposed system provides a smart and automated solution for traffic surveillance using Raspberry Pi, machine learning, and image processing techniques.      

The objectives of the project are:

• To design and develop an automated traffic surveillance system using Raspberry Pi.

  • To detect whether a bike rider is wearing a helmet using machine learning techniques.

  • To identify triple riding on a two-wheeler using image processing.

  • To detect wrong-side driving of motorcycles.

  • To display the detected violation information on an LCD module.

  • To capture images of traffic rule violations and send them automatically via email.

  • To improve road safety by assisting authorities in monitoring traffic violations efficiently.

        The major building blocks of this project are:

• Power supply.
• Raspberry pi3A+.
• SD card.
• Pi camera.
• Buzzer.
• LCD display.

      Software’s used:  

• Python language.
• OpenCV image processing.
• Linux OS.
• CNN machine learning.

     

video: