Not a mute bystander, not an apathetic audience, but your reliable Watchman.

Do you know how much time it takes for a crowd to turn into a mob? Less than a second. A simple push can lead to a fight. A simple fight can lead to death. During the 2007 Davis Cup rubber between Chile and Argentina held in Movistar Arena, the Chilean crowd booed the Argentinian team and pelted Argentinian players and officials with fruit, coins, and plastic chairs, causing numerous delays.

In public places, violent behaviors pose a serious threat to personal security and social stability. It is very important to automatically detect violence in video surveillance scenarios, for instance even in railway stations, gymnasiums, stadiums, dark and dingy street alleys, and psychiatric centers. Our web app, Watchman, helps in the detection of unruly public behavior of crowds and individuals and alerts the concerned authorities, thus generating a means of timely action to prevent grievous injuries, accidents, and eventual death.

• Python
• Django
• Keras CNN (Convolutional Neural Net)
• LSTM (Long Short Term Memory)
• HTML/CSS/Js
• Bootstrap

• Clone the GitHub repository:

$ git clone https://github.com/ASHWarriors/Watchman.git

• Install dependencies from requirements.txt using command

$ pip install -r requirements.txt

• Open Powershell or CMD terminal if using Windows, in the directory containing "Watchman" set-up the Django server by running the following command.

$ python manage.py runserver

• Open up Google Chrome and type in localhost:8000\.

Watchman is up and running!

• Click on “Start Detection” to enable violence detection.

Click here to view demo video