Re: [OSM-talk] Learning to Use Machine Learning - A learn along for folks who want to be using ML in their work.
Hi Christoph, Thank you very much adding that notice, I was sure someone would :) There are also a tremendous about of use cases for these tools that do not involve putting data in OSM. But rest assure, myself and everyone I interact with know about the guidelines and no one suggests ever not following them. These are really the early efforts to "operationalize" or create workflows for different use cases. Those guidelines will always be the core of any workflow that puts data in OSM I am quite sure. Thank you for doing the responsible thing and reminding us all. Cheers Blake On Thu, Aug 9, 2018 at 9:54 AM, Christoph Hormann wrote: > > As a quick reminder to any mapper who wants to use algorithmically > generated data as a source for mapping work: > > If you upload such data without manually verifying the individual > features against local knowledge or suitable primary data you are doing > a mechanical edit or import and must follow the rules we have for > those: > > https://wiki.openstreetmap.org/wiki/Automated_Edits_code_of_conduct > https://wiki.openstreetmap.org/wiki/Import/Guidelines > > Practically this would for example be the case if - when being asked > about the validity of your mapping by a fellow mapper - you'd be > inclined to answer "I don't know, that's what the algorithm generated". > You would then be in the mechanical edit/import domain. > > This is not a new topic, we have had this kind of problem in the past on > several occasions, for example with use of automated tracing tools like > scanaerial - which can be used both productively and responsibly for > manual mapping as well as for doing bad quality mechanical > edits/imports. And in particular with algorithms advertised with the > terms 'learning' and 'intelligence' implying human like capability and > thereby a lack of need for human control and verification this is > important to keep in mind. > > If you are not controlling the algorithm yourself but are being given > pre-generated data by others for the purpose of uploading it to OSM - > with or without manual verification - you are always doing an import > and need to follow the guidelines. > > Side note: It would be a responsible thing to include a reminder like > what i wrote above with a message like the one i reply to here or in > the welcome messages/FAQs etc. of dedicated communication channels. > > -- > Christoph Hormann > http://www.imagico.de/ > > ___ > talk mailing list > talk@openstreetmap.org > https://lists.openstreetmap.org/listinfo/talk -- Blake Girardot Humanitarian OpenStreetMap Team ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Learning to Use Machine Learning - A learn along for folks who want to be using ML in their work.
sent from a phone > On 9. Aug 2018, at 15:54, Christoph Hormann wrote: > > If you are not controlling the algorithm yourself but are being given > pre-generated data by others for the purpose of uploading it to OSM - > with or without manual verification - you are always doing an import > and need to follow the guidelines. +1 Also if you are controlling the algorithm yourself but are not manually and individually verifying its outcome, you are performing an import. cheers, Martin ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
Re: [OSM-talk] Learning to Use Machine Learning - A learn along for folks who want to be using ML in their work.
As a quick reminder to any mapper who wants to use algorithmically generated data as a source for mapping work: If you upload such data without manually verifying the individual features against local knowledge or suitable primary data you are doing a mechanical edit or import and must follow the rules we have for those: https://wiki.openstreetmap.org/wiki/Automated_Edits_code_of_conduct https://wiki.openstreetmap.org/wiki/Import/Guidelines Practically this would for example be the case if - when being asked about the validity of your mapping by a fellow mapper - you'd be inclined to answer "I don't know, that's what the algorithm generated". You would then be in the mechanical edit/import domain. This is not a new topic, we have had this kind of problem in the past on several occasions, for example with use of automated tracing tools like scanaerial - which can be used both productively and responsibly for manual mapping as well as for doing bad quality mechanical edits/imports. And in particular with algorithms advertised with the terms 'learning' and 'intelligence' implying human like capability and thereby a lack of need for human control and verification this is important to keep in mind. If you are not controlling the algorithm yourself but are being given pre-generated data by others for the purpose of uploading it to OSM - with or without manual verification - you are always doing an import and need to follow the guidelines. Side note: It would be a responsible thing to include a reminder like what i wrote above with a message like the one i reply to here or in the welcome messages/FAQs etc. of dedicated communication channels. -- Christoph Hormann http://www.imagico.de/ ___ talk mailing list talk@openstreetmap.org https://lists.openstreetmap.org/listinfo/talk
[OSM-talk] Learning to Use Machine Learning - A learn along for folks who want to be using ML in their work.
Dear Friends, In case you missed it, Dale Kunce tweeted this out yesterday: The day of Machine Learning and OSM/Humanitarian mapping reckoning is getting closer. Very excited for the possibilities these new methods have for @hotosm @RedCross. Next frontier is making HOT and @TheMissingMaps more valuable than just a training dataset for the machines. https://twitter.com/calimapnerd/status/1027275305440829440 Toward that end, I have been watching and in some cases working with various ML tool chains over the past 2 years and really, not having a lot of luck with my level of skill and knowledge. I am a pretty advanced sysadmin, comfortable on the command line, but understanding the terminology and installations has been a bit beyond me. So if anyone is like me and sees all of these great tool chains and would like to learn how to use them with your peers learning along with you and hopefully some experts as well, I created a dedicated #mlearning-basic channel on the OSM-US slack ( https://osmus-slack.herokuapp.com/ ) OSM-US runs a lovely, informative, lively, international slack with many channels and everyone is welcome! The #mlearning-basic channel is for the absolute beginner basics, how to install and use the existing and emerging tools chains and OSM/OAM data to generate usable vector data from Machine Learning quickly. You are all invited to join, but it is very basic. Hopefully some of the ML experts from the projects below will be in there to hand hold us newbies through actually making use of what we are seeing more and more everyday. Excellent tool chains exist, world changing tool chains, now we just need to get them into the hands of the people who need and want to use them everyday :) Everyone is welcome and encouraged to join, it is intended to be kind of a "learn-a-long". Our first project, my first project, is building on the Anthropocene Labs work and doing the same area using MapBoxes RobotSat tool chain using Danial's and Maning's posts as a guide. For reference please see this incredible work the community has shared in the past months, much like humanitarian mapping in general, the projects you see below will start changing the world over the next 12 months. Apologies if I missed any other OSM ML public projects, please reply and let us all know! = Anthropocene Labs @anthropoco #Humanitarian #drone imgs of #Rohingya refugee camps + pretrained model finetuned w @hotosm data. Not perfect maps but fast, small data need, works w diff imgs. Thx @UNmigration @OpenAerialMap @geonanayi @WeRobotics 4 #opendata & ideas! #cloudnative #geospatial #deeplearning https://twitter.com/anthropoco/status/1027268421442883584 = This post follows Daniel’s guide for detecting buildings in drone imagery in the Philippines. The goal of this exercise is for me to understand the basics of the pipeline and find ways to use the tool in identifying remote settlements from high resolution imagery (i.e drones). I’m not aiming for pixel-perfect detection (i.e precise geometry of the building). My main question is whether it can help direct a human mapper focus on specific areas in the imagery to map in OpenStreetMap. https://www.openstreetmap.org/user/maning/diary/44462 === Recently at Mapbox we open sourced RoboSat our end-to-end pipeline for feature extraction from aerial and satellite imagery. In the following I will show you how to run the full RoboSat pipeline on your own imagery using drone imagery from the OpenAerialMap project in the area of Tanzania as an example. https://www.openstreetmap.org/user/daniel-j-h/diary/44321 = Skynet is our machine learning platform. It quickly scans vast archives of satellite and drone imagery and delivers usable insights to decisionmakers. Our partners use Skynet to reliably extract roads and buildings from images that NASA, ESA, and private satellites and drones record daily. The tool is remarkably versatile. We are experimenting with using Skynet to detect electricity infrastructure, locate schools, and evaluate crop performance. https://developmentseed.org/projects/skynet/ = Deep learning techniques, esp. Convolutional Neural Networks (CNNs), are now widely studied for predictive analytics with remote sensing images, which can be further applied in different domains for ground object detection, population mapping, etc. These methods usually train predicting models with the supervision of a large set of training examples. https://www.geog.uni-heidelberg.de/gis/deepvgi_en.html === OSMDeepOD - OpenStreetMap (OSM) and Machine Learning (Deep Learning) based Object Detection from Aerial Imagery (Formerly also known as "OSM-Crosswalk-Detection"). http://www.hsr.ch/geometalab https://github.com/geometalab/OSMDeepOD ==
[OSM-talk] Learning to Use Machine Learning - A learn along for folks who want to be using ML in their work.
Dear Friends, In case you missed it, Dale Kunce tweeted this out yesterday: The day of Machine Learning and OSM/Humanitarian mapping reckoning is getting closer. Very excited for the possibilities these new methods have for @hotosm @RedCross. Next frontier is making HOT and @TheMissingMaps more valuable than just a training dataset for the machines. https://twitter.com/calimapnerd/status/1027275305440829440 Toward that end, I have been watching and in some cases working with various ML tool chains over the past 2 years and really, not having a lot of luck with my level of skill and knowledge. I am a pretty advanced sysadmin, comfortable on the command line, but understanding the terminology and installations has been a bit beyond me. So if anyone is like me and sees all of these great tool chains and would like to learn how to use them with your peers learning along with you and hopefully some experts as well, I created a dedicated #mlearning-basic channel on the OSM-US slack ( https://osmus-slack.herokuapp.com/ ) OSM-US runs a lovely, informative, lively, international slack with many channels and everyone is welcome! The #mlearning-basic channel is for the absolute beginner basics, how to install and use the existing and emerging tools chains and OSM/OAM data to generate usable vector data from Machine Learning quickly. You are all invited to join, but it is very basic. Hopefully some of the ML experts from the projects below will be in there to hand hold us newbies through actually making use of what we are seeing more and more everyday. Excellent tool chains exist, world changing tool chains, now we just need to get them into the hands of the people who need and want to use them everyday :) Everyone is welcome and encouraged to join, it is intended to be kind of a "learn-a-long". Our first project, my first project, is building on the Anthropocene Labs work and doing the same area using MapBoxes RobotSat tool chain using Danial's and Maning's posts as a guide. For reference please see this incredible work the community has shared in the past months, much like humanitarian mapping in general, the projects you see below will start changing the world over the next 12 months. Apologies if I missed any other OSM ML public projects, please reply and let us all know! = Anthropocene Labs @anthropoco #Humanitarian #drone imgs of #Rohingya refugee camps + pretrained model finetuned w @hotosm data. Not perfect maps but fast, small data need, works w diff imgs. Thx @UNmigration @OpenAerialMap @geonanayi @WeRobotics 4 #opendata & ideas! #cloudnative #geospatial #deeplearning https://twitter.com/anthropoco/status/1027268421442883584 = This post follows Daniel’s guide for detecting buildings in drone imagery in the Philippines. The goal of this exercise is for me to understand the basics of the pipeline and find ways to use the tool in identifying remote settlements from high resolution imagery (i.e drones). I’m not aiming for pixel-perfect detection (i.e precise geometry of the building). My main question is whether it can help direct a human mapper focus on specific areas in the imagery to map in OpenStreetMap. https://www.openstreetmap.org/user/maning/diary/44462 === Recently at Mapbox we open sourced RoboSat our end-to-end pipeline for feature extraction from aerial and satellite imagery. In the following I will show you how to run the full RoboSat pipeline on your own imagery using drone imagery from the OpenAerialMap project in the area of Tanzania as an example. https://www.openstreetmap.org/user/daniel-j-h/diary/44321 = Skynet is our machine learning platform. It quickly scans vast archives of satellite and drone imagery and delivers usable insights to decisionmakers. Our partners use Skynet to reliably extract roads and buildings from images that NASA, ESA, and private satellites and drones record daily. The tool is remarkably versatile. We are experimenting with using Skynet to detect electricity infrastructure, locate schools, and evaluate crop performance. https://developmentseed.org/projects/skynet/ = Deep learning techniques, esp. Convolutional Neural Networks (CNNs), are now widely studied for predictive analytics with remote sensing images, which can be further applied in different domains for ground object detection, population mapping, etc. These methods usually train predicting models with the supervision of a large set of training examples. https://www.geog.uni-heidelberg.de/gis/deepvgi_en.html === OSMDeepOD - OpenStreetMap (OSM) and Machine Learning (Deep Learning) based Object Detection from Aerial Imagery (Formerly also known as "OSM-Crosswalk-Detection"). http://www.hsr.ch/geometalab https://github.com/geometalab/OSMDeepOD ==
