StreetSpecter

StreetSpecter is an innovative AI-driven solution designed to detect potholes and facilitate road maintenance. Leveraging advanced technologies, StreetSpecter aims to ensure efficient and proactive road safety measures, making streets safer for everyone.

Features

• Pothole Detection
• Automatically identifies potholes using Computer-Vision.
• Reports severity levels and location.
• Real-time Monitoring
• Continuously monitors road conditions.
• Sends alerts for dangerous areas.
• User-friendly Interface.
• Easy navigation and reporting.
• Set up alerts for specific areas or severity levels.

Yolov8s training Stats

• Model Trained in Colab (T4 GPU) on 5493 Images for 25 epochs in 1.63 hours, Validated on 1698 Images.

• Training Results

1. Results

   

2. Confusion matrix (

   

3. Val Batch 0

   

StreetSpecter Application Snaps

Instructions to use

Prerequisites

Ensure you have the following installed:

• Python 3.x
• pip
• virtualenv

Installation

1. Clone the repository:

   git clone https://github.com/Spyrosigma/StreetSpecter

2. Create Virtual Environment

   pip install virtualenv  #If Virtual Env Module is not installed
   virtualenv envname      # Replace 'envname' with your preferred environment name
   envname\scripts\activate

3. Install Libraries

   pip install -r requirements.txt

4. Create a .env file and add your own Supabase Keys.

   SUPABASE_KEY='YOUR_API_KEY'
   SUPABASE_URL='YOUR_URL_KEY'

5. Run the app!

   python app.py