This project implements a robust face counting system using the YOLO (You Only Look Once) deep learning object detection architecture. The goal is to accurately count faces in various environments and conditions, potentially useful in scenarios like crowd monitoring, security surveillance, and demographic data collection.
- Real-time face detection and counting.
- Utilizes the powerful YOLO algorithm for accurate detection.
- Can process images and video streams.
- Python 3.6 or higher
- Dependencies listed in
requirements.txt
- Clone this repository:
git clone https://github.com/kudratbekkamoldinov/Counting_face_with_YOLO.git
- Navigate to the cloned repository directory:
cd Counting_face_with_YOLO - Install the required dependencies:
pip install -r requirements.txt
- To count faces in an image:
python face_counting.py --image path_to_image
- To count faces in real-time using a webcam:
python face_counting.py --webcam
- To count faces in a video file:
python face_counting.py --video path_to_video
The pretrained YOLO models (best.pt and last.pt) can be found in the runs/detect/train/weights directory. The best.pt model is used by default.
The test.csv file contains the annotations used for testing the model.
Contributions to this project are welcome! Please fork the repository and submit a pull request with your proposed changes.
This project is licensed under the MIT License - see the LICENSE.md file for details.
- The YOLO creators for their groundbreaking work in real-time object detection.
- Contributors and community for continuous improvements.