Map Features in OpenStreetMap with Computer Vision

Re:Map Features in OpenStreetMap with Computer Vision by boredpudding on Saturday March 22, 2025 @05:21PM (#43448740)

I don't understand the 'human verification' aspect.

Your docs show a simple image where the user can choose to keep a new object or not. [0] Afterwards it says: "The ones you chose to keep will be uploaded to OpenStreetMap using upload_osm.". This is uploading features automatically. The fact that it asks 'are you sure' is just silly. We all know if humans have to click yes 90% of the time, and no 10% of the time, they'll miss a lot of no's.

The image also proofs that:

- You don't see any polygons properly. You just see a an image of where the pool is. Already on the image I can see that if the polygons align to that image, it will be a total mess.

- You don't see any polygons further away from the object.

Both these points are in stereo's reply that the resulted data was a mess.

Please consider pulling the project. This will generate a lot of data that volunteers will have to check and revert.

[0] https://github.com/mozilla-ai/osm-ai-helper/blob/main/docs/s...

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by daavoo on Saturday March 22, 2025 @05:26PM (#43448775)

> This will generate a lot of data that volunteers will have to check and revert.

This is just not true. The data can be easily identified with the `created_by` tag. And I have been reviewing myself any data uploaded with the demo (with a clear different criteria on what is good enough)

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by karlgkk on Saturday March 22, 2025 @09:04PM (#43450099)

adding a "created_by" tag is not opt in. it's opt out. you are de facto choosing how OSM volunteers must approach their work, without their consent.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by AyyEye on Saturday March 22, 2025 @09:08PM (#43450130)

Can I suggest also adding a tag for ML originated features that's not specific to your demo/app? Maybe this can help put extra eyes on them and/or help prevent them from polluting the DB wholesale. Maybe client apps could have a toggle to allow/reject them.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by xorcist on Sunday March 23, 2025 @08:39AM (#43452500)

If the upstream project thinks there may be a potential problem with this, that is a problem in itself. Try not to get defensive about it, just pull the project and have another go at the problem in collaboration with upstream. Perhaps parts of the project and be useful for upstream? Perhaps another workflow could make the project better?

We all strive for better open data. I upstream feel there is a risk that automated uploads could be easier with this project, creating more boring work for them which is already enough of a problem, that animosity will be a net negative for everyone in this space. Technical solutions such as new tags or opt out schemes will not solve the problem.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by hartator on Sunday March 23, 2025 @11:43AM (#43453665)

Mozilla engineers think they are way better than the rest of us though. Don’t need to follow the same rules.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by frozenseven on Sunday March 23, 2025 @04:53PM (#43455829)

The real "problem" here is that someone is once again upset about AI for no good reason. A good cue to consider making an AI-based competitor to OpenStreetMap.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by tga_d on Sunday March 23, 2025 @06:00PM (#43456240)

The OSM community has had extremely clear rules around automated edits for most of its existence. Every experienced mapper has seen first-hand the sorts of problems they can cause. The fact that it's using AI in this instance does not give any sort of exception to these rules. To emphasize, there are already AI-assisted tools that are allowed,[0] this isn't a blanket application of "no AI ever," it's about doing so properly with the right community vetting.

[0] Most notably: https://wiki.openstreetmap.org/wiki/Rapid

Edit to add: To be clear, they have since taken steps to try to resolve the concerns in question, the discussion is ongoing. I suspect at the end of this we will get a useful tool, it's just off to a rocky start.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by crooked-v on Sunday March 23, 2025 @05:03PM (#43455895)

The "good reason" is that OSM is supposed to contain real data, not wobbly AI guesswork data.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by frozenseven on Sunday March 23, 2025 @05:15PM (#43455965)

Robust computer vision is not guesswork, and probably better than what the average contributor can do. The "wobbly" concerns were already addressed.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by wiml on Sunday March 23, 2025 @05:47PM (#43456167)

That's not an assertion I'm going to take seriously without evidence.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by frozenseven on Sunday March 23, 2025 @06:04PM (#43456258)

Preliminary evidence seems very good. The gatekeepers are already doing damage control.

[ Parent | on HN ]

Re:Map Features in OpenStreetMap with Computer Vision by wiml on Sunday March 23, 2025 @06:39PM (#43456478)

Link the evidence, then. Numbers, not vibes.

[ Parent | on HN ]