Skip to content

Real-time parking detection uses machine learning on cameras/drones to categorize spots as vacant or occupied, displayed via digital means. Benefits include reducing congestion and improving efficiency. Open-source libraries like TensorFlow and OpenCV on GitHub are used to fine-tune pre-trained models for implementation.

Notifications You must be signed in to change notification settings

A-Akhil/Real-time-parking-detection-using-machine-learning

Repository files navigation

Parking Lot Detection System using YOLOv5

This system uses the YOLOv5 object detection algorithm to detect and count the number of cars parked in a parking lot. It can be used in various scenarios such as automated parking management systems, parking lot occupancy detection, etc.

Installation

To use this system, you will need to have the following installed:

Python 3.6 or higher
PyTorch 1.7 or higher
OpenCV
YOLOv5

You can install these dependencies using the following command:

pip install -r requirements.txt

Usage

Clone the repository to your local machine.
Navigate to the parking_lot_detection directory.
Place your input video in the input directory.
Run the Main.py

Customization

If you wish to customize the detection settings, you can modify the main.py file. For example, you can change the confidence threshold or the path to the YOLOv5 weights file.

Credits

This project is based on the YOLOv5 object detection algorithm by Ultralytics LLC

Please support the development by donating.

BuyMeACoffee

About

Real-time parking detection uses machine learning on cameras/drones to categorize spots as vacant or occupied, displayed via digital means. Benefits include reducing congestion and improving efficiency. Open-source libraries like TensorFlow and OpenCV on GitHub are used to fine-tune pre-trained models for implementation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages