Even in a futuristic world, crime exists. First responders currently rely on reports from human witnesses. However, this communication is much too slow in an emergency. The lag in response times can end up being fatal. If first responders immediately get notified about a potential threat, it can prevent many deaths and reduce crime rates. IWitness aims to be the means to execute this vision.
IWitness is a web application aimed at first responders. It is designed to hook up to cameras around the city to detect crime or medical emergencies. Once the AI detects one of those, it pings a suitable person to check the situation accordingly.
We used HTML and CSS for the front end. Javascript was used in the backend.
It was our first time using TensorFlow, so it took us a while to understand how to utilize the library within our program. Most of our team started with little experience in web development, which meant we came across many hurdles that we had to utilize Google to get through.
We are proud that we were actually able to implement everything that we planned out and that our finished product turned out quite well.
We learned the basics of TensorFlow and machine learning and became more comfortable working with languages such as HTML, CSS, and JavaScript.
We plan on tuning the detector to make it more accurate and precise at assessing the situation. We plan on moving beyond just the image to get other inputs as well such as sound to increase reliability. We could also try to expand the reach of this project by creating a server to hold all the footage and to connect it with many cameras in the city.
Username: admin@gmail.com
Password: password