Inspiration
To inform/assist blind people with what objects are there in their surrounding realtime.
What it does
Given a video stream it reads all the different objects/labels present in the video.
How we built it
Used the video intelligence API and the text to speech API
Challenges we ran into
Using the google cloud platform APIs
Accomplishments that we're proud of
A working of something we intended to make.
What we learned
How to use the GCP APIs
What's next for Video-Reader
Try have live stream and a concurrent output in text form of the what the video contains
Log in or sign up for Devpost to join the conversation.