Your browser is unsupported

We recommend using the latest version of IE11, Edge, Chrome, Firefox or Safari.

AI Dashcam

Team Members Heading link

  • Sean Atangan
  • Eric Escobedo
  • Sai Arkar Khant
  • Anh Minh Ngo

Project Description Heading link

According to www.fbi.gov in 2016, more than 460,000 children are reported missing every year. In order to combat this more effectively, we decided to build an AI dashcam using transfer learning to help law enforcement identify cars described in an amber alert. This device is not only useful for this purpose, but also for quickly detaining suspects of human trafficking, grand theft auto, and other crimes involving the use of automobiles. Using the descriptions provided for the amber alert car, the device processes its field of vision and searches for that specific car. Our device uses a camera to take pictures of vehicles in front of it, and processes these images through a neural network to see if a car’s features match the suspected traits detailed by the amber alert. At the end of our development cycle, we were able to successfully train our neural network to identify different cars based on their model.

See supporting documentation in the team’s Box drive.