[eyasu6464]

I’m thinking about adding new features. Which one is more useful and should come next: searching with an image of an object, detecting changes over time using Sentinel-2 data, or detecting object in all Google Street View images within a selected area?

[notahacker]

Depends what you're going for. Change detection has a lot of established use cases but not sure whether LLM interfaces will add usability or remove accuracy; object detection in Google Street View images sounds cool and novel, but not sure what the actual use case is...

[thenthenthen]

Searching with an image of an object 100%!! (Or just like, find similar areas from a sat crop/screenshot!