DroidCamMovementDetector

YOLO Object Detection with Alarm System

This project implements a real-time object detection system using YOLO (You Only Look Once) and OpenCV. It captures video from a DroidCam, processes the frames to detect objects, and triggers an alarm if a person is detected.

Features

• Real-time object detection using YOLOv3.
• Alarm system that plays a sound when a person is detected.
• Adjustable frame size and FPS settings.
• Full-screen mode for the video display.
• Toggle alarm mode and stop alarm sound with keyboard inputs.

Installation

1. Clone the repository:

   git clone https://github.com/Anthony01M/DroidCamMovementDetector.git
   cd DroidCamMovementDetector

2. Install the required dependencies:

   pip install -r requirements.txt

3. Download YOLOv3 weights and configuration files:

   • Download the YOLOv3 weights from here.
   • Download the YOLOv3 configuration file from here.
   • Place these files in the models/yolo directory.

4. Download COCO names file:

   • Download the COCO names file from here.
   • Place this file in the models/yolo directory.

5. Download Alert Sound:

   • Download an alert sound file (e.g., alarm.wav) from here
   • Place this file in the alert directory.

6. Install DroidCam Client:

   • Download and install the DroidCam Application on your Android device from here.

7. Fix Configuration:

   • Open the config.yml file and update every filed as needed.

Usage

1. Run the script:

   python main.py

2. Keyboard Controls:

   • Press t to toggle alarm/detection mode.
   • Press g to stop the alarm sound.
   • Press f2 to toggle full-screen mode.
   • Press q to quit the application.

Disclaimer

This project is intended for educational purposes only. It should not be used for any malicious activities or to invade anyone's privacy. The authors are not responsible for any misuse of this software.

License

This project is licensed under the MIT License. See the LICENSE file for details.