What image/video training data is hardest to find right now? [R]

I'm building a crowdsourced photo collection platform

(contributors take photos with smartphones, we auto-label

with YOLO/CLIP + enrich with 40+ metadata fields per image

including weather, time, GPS, OCR).

Before I decide what to collect first, I want to know:

what image data do YOU wish existed but doesn't?

Some ideas I'm considering:

- European street scenes (no dataset covers Switzerland/France)

- Supermarket shelves with OCR-extracted prices

- Analog utility meters

- Restaurant menus with prices

- EV charging stations by type

What would YOU actually use?