sujallimje / mahakumbh_25

Cutting-edge crowd surveillance system developed for Prayagraj Mahakumbh Hackathon 2025. Utilizes advanced computer vision for head counting, anomaly detection, and fire detection in real-time, ensuring event safety and security. Proud finalists, dedicated to leveraging technology for positive impact.

Crowd Surveillance System

Overview

This project was developed for the Prayagraj Mahakumbh Hackathon 2025, with a focus on crowd surveillance. In large-scale events like the Mahakumbh, ensuring the safety and security of attendees is paramount. Our system utilizes advanced computer vision techniques to monitor crowd behavior, detect anomalies, and identify potential hazards in real-time. By providing event organizers and security personnel with valuable insights, we aim to enhance crowd management and improve overall safety measures.

Output Video Playlist : Youtube

Features

• Crowd Counting: Accurately counts heads within crowded spaces, aiding event organizers and security personnel in crowd management. This feature provides real-time data on crowd density, helping organizers make informed decisions to prevent overcrowding and ensure the safety of attendees.

• Anomaly Detection: Utilizes machine learning algorithms to identify anomalies within crowds, enabling real-time detection of suspicious behavior for proactive intervention. Whether it's detecting individuals moving against the flow of the crowd or identifying abandoned objects, this feature helps security teams identify potential threats and take timely action.

• Fire Detection: Integrated fire detection capabilities allow for the rapid identification of fire hazards within crowded areas, mitigating risks and ensuring the safety of attendees. By leveraging image processing and deep learning techniques, our system can detect flames or smoke in the early stages, enabling prompt evacuation and firefighting measures.

Installation

1. Clone the repository:

   git clone https://github.com/Kanishk3813/Mahakumbh_25.git

• Install necessary python libraries by (pip install {library_name}) .

Sample Output Images

Here are some sample output images generated by our crowd surveillance system:

• Crowd Counting

• Crowd Anomaly

• Fire Detection

Contributors

• Vinayak Soni (https://github.com/vinayaksoni1729)
• Kanishk Reddy (https://github.com/Kanishk3813)
• Sujal Limje (https://github.com/sujallimje)
• Sudipta Bag (https://github.com/sudiptabag2004)

Contributing

Contributions are welcome! If you'd like to contribute to the Crowd Surveillance System, please follow these steps:

1. Fork the repository.
2. Create a new branch (git checkout -b feature/your-feature-name).
3. Make your changes and commit them (git commit -am 'Add new feature').
4. Push your changes to your forked repository (git push origin feature/your-feature-name).
5. Create a pull request detailing your changes and their purpose.