video-intelligence-demo | Video Intelligence API keynote demo from Google Next

Create a Cloud project
Enable the Video Intelligence API
Enable Cloud Functions
Generate a JSON keyfile
In your project, create four Cloud Storage buckets: one for your videos one for the video JSON output one for the video thumbnails one as a staging bucket for your Cloud Function
Set permissions for your Storage Buckets Make video bucket world readable - Group - allUsers - Reader Make JSON annotation bucket writable by service account - User - [serviceaccount] - Owner
Make copy of frontend/local.sample.json named frontend/local.json
Make copy of backend/local.sample.json named backend/local.json
Copy your Cloud project ID and storage bucket names into frontend/local.json and backend/local.json
Copy your generated service account json file into a file called keyfile.json and place a copy in both your frontend AND backend directories (you'll deploy these separately, one to App Engine and one to Cloud Functions)
Clone this repo
cd into the frontend directory
Run npm install to install dependencies
Run npm start in one tab on your terminal
Create a new tab and gulp dev init
Make sure npm start and gulp are running at the same time
Navigate to localhost:8080. You should see the UI without any videos - that part is next!
(Optional step) If you want to see the UI with some sample video content before deploying your function and adding your own videos, copy the files from the sample-annotations directory into your storage buckets: Copygoogle-home-superbowl.mp4 into your video storage bucket Copy google-home-superbowlmp4.json file to your video JSON annotation storage bucket Copy both png files into your thumbnail bucket Run the frontend and you'll see the video with the annotations visualized