SimpleTrafficLightClassification

The most simple traffic light classification CNN machine learning model.

Overview

This project demonstrates a basic Convolutional Neural Network (CNN) model for classifying traffic lights into three categories:

• Go (Green light)
• Stop (Red light)
• Slow (Yellow light)

The model is lightweight and designed for straightforward implementation, suitable for absolute beginners and those exploring computer vision concepts in machine learning.

Features

• Easy to understand: Designed with simplicity in mind to make it accessible for learners.
• Fast training: Optimized for quick experimentation and iteration.
• Basic preprocessing: Includes fundamental steps to prepare data for training.

Project Motivation

The goal of this project is to create a simple yet functional machine learning model for recognizing traffic lights. This prototype can serve as a starting point for more complex systems, such as those assisting the visually impaired or autonomous vehicles.

Usage

1. Preprocess the dataset

2. Train the model

3. Test the model

4. Evaluate the performance of the model using metrics such as accuracy or F1-score.

Model Architecture

The CNN model consists of:

• Convolutional layers for feature extraction.
• MaxPooling layers for dimensionality reduction.
• Fully connected layers for classification.

The architecture has been kept simple for educational purposes.