# AI Road Condition Classifier: Pothole Detection Project
> Discover how AI-driven image classification using Teachable Machine can monitor infrastructure and identify potholes for safer road maintenance.

Tags: ai, civil-engineering, image-classification, infrastructure-monitoring, pothole-detection, machine-learning
## Slide 1: Road Condition Classifier
- Project title: Road Condition Classifier (Good / Pothole)
- Methodology: Image Classification using Teachable Machine
- Institution: East West Institute of Technology, 2025–26

## Slide 2: Introduction
- Potholes significantly impact safety and vehicle performance.
- Manual road inspection is time-consuming and expensive.
- Automated image-based classification offers an economical solution.

## Slide 3: Problem Statement & Objectives
- Goal: Automatically identify road conditions as 'Good' or 'Pothole' from images.
- Objectives: Collect road data, train a classification model, and achieve accurate results.

## Slide 4: Review of Literature
- Previous research highlights gaps in manual survey scalability.
- Deep learning and Teachable Machine facilitate coding-free ML model development.

## Slide 5: Methodology
- Process: Image collection -> Classification -> Training -> Testing -> Evaluation.
- Utilizes Google's Teachable Machine framework.

## Slide 6: Dataset & Tools Used
- Dataset: Mobile camera images captured under varied lighting.
- Tools: Google Teachable Machine, Web Browser, Mobile/Laptop.

## Slide 7: Model Training
- Architecture: Convolutional Neural Network (CNN).
- Features: Real-time preview and testing with unseen images.

## Slide 8-10: Results & Conclusion
- Model achieved high accuracy in identifying good roads and potholes.
- Proved effective for preliminary road condition assessments in civil engineering.

## Slide 11: Future Scope
- Potential for multi-class detection (cracks, waterlogging).
- Integration with GIS or drone-based imagery.
---
This presentation was created with [Bobr AI](https://bobr.ai) — an AI presentation generator.