CCTV People Counter is a Python application that uses YOLO (You Only Look Once) object detection and tracking to count the number of people in a video and display the results in a user-friendly way.
- Upload a video file for processing.
- Utilizes YOLO object detection and tracking to count the number of people.
- Converts the output video to H.264 format for compatibility.
- Displays the processed video and average count in the web interface.
- Includes a progress bar and spinner loader to provide visual feedback during processing.
Ensure you have the following prerequisites installed:
- Python 3.8+
- Streamlit (can be installed via pip)
- OpenCV (can be installed via pip)
- FFmpeg for video conversion (installation may vary by platform)
- The YOLO model (yolov8m.pt or any other compatible model)
You can create a virtual environment and install the required packages using the provided requirements.txt:
pip install -r requirements.txt
- Clone the repository:
git clone https://github.com/QuantuM410/cctv-human-count-detection.git
- Change to the project directory:
cd cctv-human-count-detection
-
Install the required dependencies as mentioned in the Requirements section.
-
Place the YOLO model file (e.g., yolov8m.pt) in the project directory.
Run the Streamlit app with:
streamlit run app.py
- Upload a video file for processing.
- The app will display the processed video and average count.
- You can monitor the progress of video processing via the progress bar or spinner loader.