Map Features in OpenStreetMap with Computer Vision

blog.mozilla.ai

306 points by Brysonbw a month ago


stereo - a month ago

Hi from the OpenStreetMap Foundation. Please don't add AI-detected features directly to the database.

The algorithms have problems with false positives, and with mapping straight or rectangular objects as wobbly, as shown in the second-to-last screenshot.

As a helper to detect missing features, this is a precious tool. But we still need human intervention to make sure the detected objects are drawn correctly.

See also: https://wiki.openstreetmap.org/wiki/Import/Guidelines and https://wiki.openstreetmap.org/wiki/Automated_Edits_code_of_...

throwaway346434 - a month ago

Oh, great re swimming pools - solar detection is another one on my list to have a go at.

I feel like a lot of the pushback here is an idea that OSM can grow from hand mapping; but as someone with 60k changesets over a decade... no amount of human volunteer enthusiasm is to the point that it can "solve" mapping at a global scale to the standards that make the map data overwhelmingly useful.

I feel we need a scalable framework for importing and maintaining data: ways to annotate the quality, sources, where to report bugs in the data source, and guidance to consumers. Ie if I want to query "businesses of type X" "mapped by humans within the last year", I can sort of do that with "check date".

But who knows how many of those attributes are accurate, or if the mapper who checked only checked one aspect (name/location)? Would it be better to ingest alltheplaces opening hours to maintain this data automatically, every month?

Would it be better as a data consumer if I could filter to only certain sources I trust? Or I could use data - even if the polygons aren't perfect or similar, even with known limitations like "poi inferred by AI".

orbital-decay - a month ago

Experiencing automated mapping first-hand makes me extremely wary of it. I've travelled across South America on a motorcycle, and OSM has a large amount of edits there that look automated (particularly in Brazil), making it barely usable in certain places. I'm not even talking about rural roads but also fairly large cities.

ks2048 - a month ago

I did some work in this field, although years ago. There is a huge amount of existing models, datasets, tools, etc.

https://github.com/satellite-image-deep-learning

qwertox - a month ago

Google would not allow this, but Mapbox seems to be OK with this, if it is used for non-commercial purposes or OSM, and only if their satellite data is used (not their vector data):

  1.6. No Tracing, Deriving, or Extracting. Customer shall not trace or otherwise derive or extract content, data
       and/or information from the Service Offerings except that Customer may use Studio or third-party
       software to trace Mapbox Maps solely comprised of satellite imagery to produce derivative vector
       datasets (i) for non-commercial purposes or (ii) for OpenStreetMap.
Kind of nice from them.
pierotofy - a month ago

Worked on something similar a few months ago (albeit for smaller scale geographic data): https://github.com/uav4geo/GeoDeep

ySteeK - a month ago

Wait, we are not mapping things we see in sattelite images, we are mapping things that have ground truth.

Please do not contribute anything ai-fantasized

gpvos - a month ago

Can Mozilla please focus on making a good browser?

anakaine - a month ago

Id love to see a bit more detail on fine tuning SAM/2 to do things like detect pools or solar arrays. Both these are fantastic things to have mapped for community resilience projects, but I've not been able to follow along with SAM2 fine tuning at all.

I've got a Yolov8 model which does quite a good job of finding and segmenting out solar, but the edges are absolutely horrible and require an insane amount t of work to clean up. I've seen results from SAM2 that has been trained, and the results look massively better.

Wouldn't put these in OSM due to stereo6 comment about accuracy, but I could sure use them elsewhere.

daavoo - a month ago

Hello everyone, thanks for all the valuable feedback.

I have published a new release where any code to directly upload to OSM has been replaced with an export to OsmChange format.

I hope this is a step in the right direction, I will continue the discussion on the dedicated thread in the OSM forum.

ecommerceguy - a month ago

We used to call this heads up digitizing.

curtisszmania - a month ago

[dead]

banana_dick_7 - a month ago

[dead]

banana_dick_5 - a month ago

[dead]

banana_dick_4 - a month ago

[dead]

banana_dick_3 - a month ago

[dead]

banana_dick_2 - a month ago

[dead]

banana_dick_1 - a month ago

[flagged]

cratermoon - a month ago

[flagged]