Readit NewsSadly no R Soles though (A shoe shop formerly in Chelsea but now online) - however, just searching for profanities does bring back some graffiti
This doesnt really answer your question but hopefully gives some insight into our process.
The main bottlenecks were breaking the fisheye-style panoramas into different perspectives (so text was more readable), passing it to OCR and acquiring the panoramas as there isn't an official API.
Because of the above, we constrained ourselves from the outset. For example, the spacings between panoramas was 50m, we didnt traverse residential roads that were less likely to have signage, we only used the most recent panorama for a location etc
If I interpret global as without those constraints (5m spacings, every road, all historic panoramas) then I think the first problem you'll run into is being rate limited by Google. Compute may be able to solve the other problems but it would be very expensive.
I documented a few examples of this a while ago, which demonstrate how easily these systems could leak journey data.
https://dfworks.xyz/blog/online_stalking_citymapper/https://dfworks.xyz/blog/pizza_order/
All Text in NYC - https://news.ycombinator.com/item?id=42367029 - Dec 2024 (4 comments)
All text in Brooklyn - https://news.ycombinator.com/item?id=41344245 - Aug 2024 (50 comments)
I then modelled how these fictional devices might vote to demonstrate how harmful/useful aggregated and analysed MAID data can be.
https://maps.app.goo.gl/jmJ1qhQsB3AetLiK8
But doesn't find this billboard, probably because it doesn't actually contain the text "Batman".
https://maps.app.goo.gl/nBoHArvaKZSgRH5W7
It should be able to match text query to anything, not just text.
It feels like there could potentially be some town planning applications like finding the distribution of rubbish bins vs litter on the floor