Upload a video (< 250 MB), then ffmpeg is used to extract images from the video, specify the number of frames per second. A value of 0.125 means one frame every 8 seconds. Then using the keras package a VGG16 pre trained network is used to tag the extracted images. For each image the top 3 tags are returned

Cheers, Longhow

images taken from video

Video info and Overview of tags extracted