A mobility aid app that uses computer vision to detect obstacles for visually impaired users
Design
safeStride is a mobile application that uses computer vision to detect obstacles in the path of
visually impaired users. The app uses the camera on a smartphone to capture real-time video
feed, which is then processed using a pre-trained machine learning model to identify potential
obstacles. When an obstacle is detected, the app provides audio feedback to the user, alerting
them to the presence and location of the obstacle. The app is designed to be user-friendly and
easy to use, with a simple interface that allows users to quickly start and stop the obstacle
detection feature. The app also includes customizable settings, allowing users to adjust the
sensitivity of the obstacle detection and choose from different audio feedback options.
The app was developed using Python and TensorFlow, with a focus on creating a lightweight and
efficient model that could run on a smartphone without requiring significant processing power.
The app was tested with visually impaired users, who provided valuable feedback on its usability
and effectiveness. Overall, safeStride is a promising tool for improving mobility and
independence
for visually impaired individuals.
