Boundary Effects about usbuildingfootprints

[nitrif]

Thanks @simonjchapman for pointing this out. I'll follow up unce we track this down.

[nmpeterson]

FWIW, this is a problem in Chicago, too.

[chrisbnyc]

+1 on this, would love it (if possible) for the missing tiles to be included. This data is great to have, thanks again!

[vvascanus]

There are also tile-shaped gaps all along I-15 in Connecticut.

[chrisbnyc]

I've looked at several states, it appears to be any major metropolitan area has these gaps. I'd imagine it is something in the workflow that will be fixed for all when one is fixed.

[nitrif]

The gap areas contain image tiles taken with different cameras, which is causing the creation of artificial edges between neighboring tiles. These confuse our detection network which hasn't learned to deal with them.
We took a very conservative approach of skipping such tiles. I think we could add aditional effort in order to properly deal with this problem.

[simonjchapman]

Very interesting. Might it be good to relax your approach and output these tiles as a "delta"? That would also allow members of this group to help you with validating their quality and also not disrupt the integrity of the currently published set.

Thanks again for your efforts in this area.

[nitrif]

Fixed in the latest release.

[dwtkns]

It looks like this may still be happening in a few spots in the 1.1 release. I noticed it in the Texas, California, and Colorado data:

Around downtown Houston:

In L.A., south of the Hollywood Hills:

Some more hard-to-see artifacts around San Jose:

And around downtown Denver:

[antifa-ev]

@simonjchapman How have you generated your renderings? I'm looking for the right software ...

[chrisbnyc]

In at least the San Jose example, it looks like it is being too conservative for the edge of East Capitol Freeway:

looks like it tracks to the 101 just fine but there's a nice hard edge on the imagery (used by Apple Maps)

[ajblen13]

Great work pulling this all together. Just wanted to make you aware that we're seeing similar issues near Minneapolis/St. Paul.

[Kmthenry]

Incredible dataset! Likewise, Louisville Kentucky.