AI-Powered Vision Assistance Prototype

For our FSE 100 project at Arizona State University, my team was tasked with creating a solution for a specific group of people. After hearing the interviews we were provided, we realized that people with vision impairments struggle with head-high objects and wanted to create a solution to help warn them before they hit an obstacle.

Our solution involved a combination of a webcam and ultrasonic sensor. The ultrasonic sensor warned of imminent danger with a loud buzzer, while the webcam was connected to an OpenAI API that detected obstacles farther away and then warned the user with vibration. The device included a button to turn it off when the user was sitting on public transit and there would be many close obstacles. We used async Python functions to allow the ultrasonic sensor to continue working while the webcam waited for a response.

The compute was done on a Raspberry Pi 4B, and the main hardware was stored in a fanny pack. The ultrasonic sensor and webcam were housed on top of a baseball cap, with the wires carefully managed.

The end result impressed the professor enough that he kept our design around as an example for next year.