VNGeneratePersonSegmentationRequest

[stephanschulz]

This is not really an issue but more a feature request ;)

What do you think it would take to also get the people segmantation information out of coreML in to OF?
https://developer.apple.com/documentation/vision/applying_matte_effects_to_people_in_images_and_video

I know on the iOS photo app you need to press on the person you want to segment. So it might need some initial coordinates ... ? If so maybe it could to be combined with landmarks detection first and after the segmentation?

Would be interesting to hear your thoughts.

Cheers, Stephan.