Gun Block: Detecting Guns in a Video Stream Using Machine-Learning

Team: 13

School: Capital High

Area of Science: Machine Learning

Proposal: Mass shootings have been a handicap of the United States for decades. We need a rapid detection and response protocol to firearms in order to keep schools and public areas safe. This is important because we want to reduce overall violence in schools.We want to implement a detection system that is fast and reliable to decrease the time between detection and response. We will create a machine learning system (artificial neural network) to detect a gun in a photographic image. We have collected thousands of individual gun images that we will use to train the machine learning system. Once trained the system would be able to search individual frames of a live video stream. If a gun is detected, this could feed into an alarm network that could lock doors or relay information to facilitate a lock down.

Team Members:

  Oscar Sandoval Torres
  German Rojo
  Edwardo Pena

Sponsoring Teacher: Irina Cislaru

Mail the entire Team