TOtoomuchtodo·Jan 2, 2018
In Show HN: Mask R-CNN Neural Network for Mapping Sport Fields in OpenStreetMaptrailbehind
DeepOSM
Python2016–2018
trailbehind / DeepOSM
DeepOSM
Train a deep learning net with OpenStreetMap features and satellite imagery.
5Distinct people
7Mentions
0Explicit recommenders
1.3KGitHub stars
What to know before exploring
What it is
Train a deep learning net with OpenStreetMap features and satellite imagery.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:03:16 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by month7 dated mentions
Observed mentions: 2016-05-09 09:46:14 UTC to 2018-01-02 16:41:05 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| May 2016 | 2016-05-01 00:00:00 UTC | 2016-06-01 00:00:00 UTC | 4 | 2 | 2 |
| Jun 2016 | 2016-06-01 00:00:00 UTC | 2016-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2016 | 2016-07-01 00:00:00 UTC | 2016-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2016 | 2016-08-01 00:00:00 UTC | 2016-09-01 00:00:00 UTC | 1 | 0 | 1 |
| Sep 2016 | 2016-09-01 00:00:00 UTC | 2016-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2016 | 2016-10-01 00:00:00 UTC | 2016-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2016 | 2016-11-01 00:00:00 UTC | 2016-12-01 00:00:00 UTC | 0 | 0 | 0 |
| Dec 2016 | 2016-12-01 00:00:00 UTC | 2017-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2017 | 2017-01-01 00:00:00 UTC | 2017-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2017 | 2017-02-01 00:00:00 UTC | 2017-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 2017 | 2017-03-01 00:00:00 UTC | 2017-04-01 00:00:00 UTC | 0 | 0 | 0 |
| Apr 2017 | 2017-04-01 00:00:00 UTC | 2017-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2017 | 2017-05-01 00:00:00 UTC | 2017-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 2017 | 2017-06-01 00:00:00 UTC | 2017-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2017 | 2017-07-01 00:00:00 UTC | 2017-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2017 | 2017-08-01 00:00:00 UTC | 2017-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2017 | 2017-09-01 00:00:00 UTC | 2017-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2017 | 2017-10-01 00:00:00 UTC | 2017-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2017 | 2017-11-01 00:00:00 UTC | 2017-12-01 00:00:00 UTC | 0 | 0 | 0 |
| Dec 2017 | 2017-12-01 00:00:00 UTC | 2018-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2018 | 2018-01-01 00:00:00 UTC | 2018-02-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
7 sources> What is the easiest way to contribute and map out these roads on OpenStreetMap?
Dunno about easiest, but the most effective is probably to just buy the detailed satellite/aerial imagery, (http://microsites.digitalglobe.com/30cm/) run some machine learning algorithms to identify roads, and upload that.
https://github.com/trailbehind/DeepOSM https://developmentseed.org/blog/2017/01/30/machine-learning...
In Quest-driven OpenStreetMap editing for AndroidThis has been heating up. Here's the seminal paper that kicked off the Cambrian Explosion: https://www.cs.toronto.edu/~vmnih/docs/Mnih_Volodymyr_PhD_Th...
And I saw two presentations about this at State of the Map US.
* Anand Thakker of Development Seed had a cool live demo: https://www.youtube.com/watch?v=BftllmqXSpA&list=PLqjPa29lMi...
* Facebook mapped a bunch of roads in Egypt, and has an ongoing effort. Facebook apparently didn't allow their's to be taped.
I have a similar project called DeepOSM: https://github.com/trailbehind/deeposm
There is starting to be a conversation in the OSM community about allowing robot edits into the map, I'm definitely pro robot. Google has been doing it for years. Mike Migurski touched off debate on the OSM Slack and blog comments with his post: http://mike.teczno.com/notes/openstreetmap-at-a-crossroads
Read the rest
.h... (added this link after maxerickson's comment reminded me what touched of the debate).
http://terrapattern.com is also a related project from some CMU people.
Custom site to start at least, I don't consider any of this really production ready yet.
Here's the app work: https://github.com/trailbehind/DeepOSM/compare/feature/deepo...
In DeepOSM: Detect roads and features in imagery with neural nets using OpenStreetMapGreat find, I'll add that to the references on DeepOSM.
Looking at that repo, the main differences are:
* that code applies to a specific (massachusetts) data set, while DeepOSM uses nationwide USA NAIPs trained against OSM extracts
* they seem to have implemented the full Mnih CNN - DeepOSM just uses a single layer as is
* Mnih didn't touch on using the infrared band
In general, that project seems more mature in replicating Mnih than DeepOSM. Our next goal is a website to show errors in OSM data to be corrected, rather than finish making the net deeper.
edit: added links to paper and code https://github.com/trailbehind/DeepOSM/commit/8053057635a1a0...
In DeepOSM: Detect roads and features in imagery with neural nets using OpenStreetMapDeepOSM: Detect roads and features in imagery with neural nets using OpenStreetMap
93 points · Open discussionDeepOSM – train a neural net with Openstreetmap features and orbital imagery
5 points · Open discussion