Multimodal Game Event Detection via Machine Learning

The partner company (AMD) is a major innovator in the field of computer graphics and visualization, they manufacture Graphical Processing Unit (GPU) which are used by many gamers around the world. While playing video games, gamers tend to perform out-of-band actions such as saving the last few minutes of gameplay after a challenging fight in a first-person shooter game. Gamers usually search for walkthroughs or FAQs when failing to complete a difficult level or scene in a video game. This project aims to use Computer Vision and Machine learning to detect such events in near real-time during a gameplay. Detection of such events can then trigger actions via AMD’s software to improve the gameplay experience of gamers who are using AMD hardware, thus providing benefit to their customers.

Faculty Supervisor:

Chris Mcintosh

Student:

Partner:

AMD Canada

Discipline:

Computer science

Sector:

Manufacturing; Professional, scientific and technical services

University:

University of Toronto

Program: