ParkSpotter

This project aims to make the parking search process faster, more efficient, and accessible with an AI-supported system.
The system stands out with real-time monitoring in marketplaces, shopping malls, and private parking lots, providing priority access for individuals with disabilities, anomaly detection, and a low-cost technology infrastructure.
Developed using Python and the YOLOv8 model, the project contributes to environmental sustainability goals while optimizing traffic flow.

Firebase Integration Warning !!

This project uses Firebase as its database to efficiently store and manage parking data.
Make sure to configure your Firebase account and provide the serviceAccountKey.json file for seamless integration.

Project Purpose

As urbanization increases, finding available parking spaces has become a significant challenge, leading to time loss, financial costs, and environmental concerns. The ParkSpotter system was developed to:

• Optimize the parking search process, making it faster and more efficient.

• Improve accessibility for disabled individuals, ensuring designated spots are used correctly.

• Provide a cost-effective and scalable AI-based solution for municipalities and private parking lots.

• Detect parking anomalies, such as unauthorized usage of reserved spots.

Features

• Image Analysis: Parking lot occupancy analysis through camera images, videos, or photos.
• Parking Spot Selection: Select parking areas via videos, live cameras, or photos.
• Real-Time Detection: Analyze live camera streams and video recordings.
• Disability-Friendly Design: Dedicated parking spot selection, tracking, and alert systems for individuals with disabilities.
• Firebase Integration: Storing analysis results in the cloud using a database connection.
• User-Friendly Interface: Easy-to-use PyQt5-based graphical user interface.
• Monitoring: Efficient parking lot management and anomaly detection.
• Parking Lot Redesign: Empowers users to redesign their parking lots, with all changes automatically saved to Firebase.

Technologies Used

• Programming Language: Python
• Machine Learning Model: Ultralytics YOLOv8
• GUI Development: PyQt5
• Image Processing: OpenCV
• Database: Firebase
• IDE: PyCharm

Usage

1. Upload Visuals: Start analysis by uploading camera images or photos.
2. Parking Spot Selection: Select parking areas via videos, live cameras, or photos.
3. Real-Time Analysis: Monitor parking lot occupancy using live camera streams.
4. Analysis Results: View results both visually and in the Firebase database.
5. Disabled Parking Spots: Select and monitor parking spots designated for individuals with disabilities.

Application Main Window

Application Analysis Example

Parking Spot Selecting

Future Improvements

• Enhance user experience and improve system accuracy.

• Improve real-time performance of the AI model.

• Optimize database operations for faster response times.

• Expand to a mobile app version for user-friendly interaction.

Contribute and Support

We are open to your suggestions and ideas to make the ParkSpotter project even better. You can contribute to the project in the following ways:

• Report Issues and Suggestions: If you encounter any problems or have improvement ideas, please open an "issue." Every piece of feedback is invaluable to us!
• Spread the Word: Share the project with your friends and anyone who might be interested, helping us reach a broader audience.

Contact

Feel free to reach out to us for more information or to share your contributions. Thank you in advance for your support!