Getting the Bounding Boxes of the Validated Regions

classic Classic list List threaded Threaded
15 messages Options
Reply | Threaded
Open this post in threaded view
|

Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

john whelan-2
Essentially you are proposing an import.  There are OpenStreetMap rules about how this should be done.  It can be done, Microsoft has released building outlines for the US which were created in this manner but the import itself is being done in sections by conventional mappers.

You will need the cooperation of the local mappers on the ground and imports of dubious quality tend to get a fair chunk of flack.  I would suggest you Google OSM imports before doing anything.

Cheerio John

On Mon, 19 Nov 2018, 10:47 pm Serkan Karakulak <[hidden email] wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Georgy Potapov
Dear John,

the question isn't about imports. Seems guys are preparing dataset to train and test models and they need to download data that's been already validated within Missing Maps,  as a "ground truth". 
Is there a way to get the precise coordinates of the areas where this job is done or projected to be done?
Me too was asking if it makes sense to apply algorithm to detect damaged buildings on imagery to leverage the mapping speed in disaster affected areas?

All the best,
Georgy

On Tue, Nov 20, 2018 at 3:29 PM john whelan <[hidden email]> wrote:
Essentially you are proposing an import.  There are OpenStreetMap rules about how this should be done.  It can be done, Microsoft has released building outlines for the US which were created in this manner but the import itself is being done in sections by conventional mappers.

You will need the cooperation of the local mappers on the ground and imports of dubious quality tend to get a fair chunk of flack.  I would suggest you Google OSM imports before doing anything.

Cheerio John

On Mon, 19 Nov 2018, 10:47 pm Serkan Karakulak <[hidden email] wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

john whelan-2
I've done a lot of validation in HOT.  Some is done by people with little experience so I don't think validated tiles would be much use to you.  Also be aware that some imagery can be three years out of date so the imagery can vary.  The sort of problems you'll run into are much of the HOT mapping is done by inexperienced mappers using iD and the buildings are more approximate than you might like especially on size and shape.  It takes four times longer to correct a building than to remap it so as a rule of thumb validators tend to stay away from projects with buildings.

Having said that have a look at the hot projects for one that is 100% complete and 100% validated.  You should be able to work out the coordinates from the project and if you are lucky it should also give you the imagery used when mapping for HOT.  Beware this OpenStreetMap and some mapping may have taken place on the ground showing buildings etc that are not on the image.

You might be better off working with an experienced mapper who can both map and check the sources.  They should also check for duplicates, there are tools available.  I suggest an area that hasn't been mapped before and map it correctly with an experienced mapper using JOSM and things like the building_tool plugin.

If you're just trying the algorithm out Ottawa in Canada has accurate buildings in OpenStreetMap.

Have fun

Cheerio John

Georgy Potapov wrote on 2018-11-20 9:25 AM:
Dear John,

the question isn't about imports. Seems guys are preparing dataset to train and test models and they need to download data that's been already validated within Missing Maps,  as a "ground truth". 
Is there a way to get the precise coordinates of the areas where this job is done or projected to be done?
Me too was asking if it makes sense to apply algorithm to detect damaged buildings on imagery to leverage the mapping speed in disaster affected areas?

All the best,
Georgy

On Tue, Nov 20, 2018 at 3:29 PM john whelan <[hidden email]> wrote:
Essentially you are proposing an import.  There are OpenStreetMap rules about how this should be done.  It can be done, Microsoft has released building outlines for the US which were created in this manner but the import itself is being done in sections by conventional mappers.

You will need the cooperation of the local mappers on the ground and imports of dubious quality tend to get a fair chunk of flack.  I would suggest you Google OSM imports before doing anything.

Cheerio John

On Mon, 19 Nov 2018, 10:47 pm Serkan Karakulak <[hidden email] wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

--
Sent from Postbox

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

pierzen
As John is saying, quality can vary a lot. You should look at the thread where I presented geometry quality analysis recently.

You need a more rigourus procedure where you can compare AI with contributors that operate in the same conditions, with the same imagery.

 
Pierre


Le mardi 20 novembre 2018 09 h 44 min 59 s HNE, John Whelan <[hidden email]> a écrit :


I've done a lot of validation in HOT.  Some is done by people with little experience so I don't think validated tiles would be much use to you.  Also be aware that some imagery can be three years out of date so the imagery can vary.  The sort of problems you'll run into are much of the HOT mapping is done by inexperienced mappers using iD and the buildings are more approximate than you might like especially on size and shape.  It takes four times longer to correct a building than to remap it so as a rule of thumb validators tend to stay away from projects with buildings.

Having said that have a look at the hot projects for one that is 100% complete and 100% validated.  You should be able to work out the coordinates from the project and if you are lucky it should also give you the imagery used when mapping for HOT.  Beware this OpenStreetMap and some mapping may have taken place on the ground showing buildings etc that are not on the image.

You might be better off working with an experienced mapper who can both map and check the sources.  They should also check for duplicates, there are tools available.  I suggest an area that hasn't been mapped before and map it correctly with an experienced mapper using JOSM and things like the building_tool plugin.

If you're just trying the algorithm out Ottawa in Canada has accurate buildings in OpenStreetMap.

Have fun

Cheerio John

Georgy Potapov wrote on 2018-11-20 9:25 AM:
Dear John,

the question isn't about imports. Seems guys are preparing dataset to train and test models and they need to download data that's been already validated within Missing Maps,  as a "ground truth". 
Is there a way to get the precise coordinates of the areas where this job is done or projected to be done?
Me too was asking if it makes sense to apply algorithm to detect damaged buildings on imagery to leverage the mapping speed in disaster affected areas?

All the best,
Georgy

On Tue, Nov 20, 2018 at 3:29 PM john whelan <[hidden email]> wrote:
Essentially you are proposing an import.  There are OpenStreetMap rules about how this should be done.  It can be done, Microsoft has released building outlines for the US which were created in this manner but the import itself is being done in sections by conventional mappers.

You will need the cooperation of the local mappers on the ground and imports of dubious quality tend to get a fair chunk of flack.  I would suggest you Google OSM imports before doing anything.

Cheerio John

On Mon, 19 Nov 2018, 10:47 pm Serkan Karakulak <[hidden email] wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

--
Sent from Postbox
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Joseph Reeves
In reply to this post by Serkan Karakulak
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
In reply to this post by pierzen
Thanks a lot for the discussions and your time. I will definitely try some quality control methods as you suggested. Sometimes more data also increase the accuracy even when it's noisy, that part is not an exact science unfortunately:) But I will try using only %100 validated tasks as you suggested. We might also try to use the algorithm we are developing for quality control, inspect the tiles that the algorithm and the current labels disagree too much, discard some of them where the labels seem to be inaccurate and train the AI model again. We can see and compare the results and accuracy afterwards. It seems that the quality will be a real concern, thanks for raising the issue and your suggestions.


On Tue, Nov 20, 2018 at 9:55 AM Pierre Béland <[hidden email]> wrote:
As John is saying, quality can vary a lot. You should look at the thread where I presented geometry quality analysis recently.

You need a more rigourus procedure where you can compare AI with contributors that operate in the same conditions, with the same imagery.

 
Pierre


Le mardi 20 novembre 2018 09 h 44 min 59 s HNE, John Whelan <[hidden email]> a écrit :


I've done a lot of validation in HOT.  Some is done by people with little experience so I don't think validated tiles would be much use to you.  Also be aware that some imagery can be three years out of date so the imagery can vary.  The sort of problems you'll run into are much of the HOT mapping is done by inexperienced mappers using iD and the buildings are more approximate than you might like especially on size and shape.  It takes four times longer to correct a building than to remap it so as a rule of thumb validators tend to stay away from projects with buildings.

Having said that have a look at the hot projects for one that is 100% complete and 100% validated.  You should be able to work out the coordinates from the project and if you are lucky it should also give you the imagery used when mapping for HOT.  Beware this OpenStreetMap and some mapping may have taken place on the ground showing buildings etc that are not on the image.

You might be better off working with an experienced mapper who can both map and check the sources.  They should also check for duplicates, there are tools available.  I suggest an area that hasn't been mapped before and map it correctly with an experienced mapper using JOSM and things like the building_tool plugin.

If you're just trying the algorithm out Ottawa in Canada has accurate buildings in OpenStreetMap.

Have fun

Cheerio John

Georgy Potapov wrote on 2018-11-20 9:25 AM:
Dear John,

the question isn't about imports. Seems guys are preparing dataset to train and test models and they need to download data that's been already validated within Missing Maps,  as a "ground truth". 
Is there a way to get the precise coordinates of the areas where this job is done or projected to be done?
Me too was asking if it makes sense to apply algorithm to detect damaged buildings on imagery to leverage the mapping speed in disaster affected areas?

All the best,
Georgy

On Tue, Nov 20, 2018 at 3:29 PM john whelan <[hidden email]> wrote:
Essentially you are proposing an import.  There are OpenStreetMap rules about how this should be done.  It can be done, Microsoft has released building outlines for the US which were created in this manner but the import itself is being done in sections by conventional mappers.

You will need the cooperation of the local mappers on the ground and imports of dubious quality tend to get a fair chunk of flack.  I would suggest you Google OSM imports before doing anything.

Cheerio John

On Mon, 19 Nov 2018, 10:47 pm Serkan Karakulak <[hidden email] wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

--
Sent from Postbox
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://urldefense.proofpoint.com/v2/url?u=https-3A__lists.openstreetmap.org_listinfo_hot&d=DwIGaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=9jC6quPZN0RnI866qaQhEg&m=CWFFLleRsuBiOUXD6gXRpreKxzA-4fxMrEBXvJSZsDo&s=7yKuZLIGwWnrZsIY7HCqPZ_3BagzqQFFGCmM5TcVFoc&e=

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
In reply to this post by Joseph Reeves
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Palolo
Serkan,

The last value is the same as the first, it closes the polygon.

On Tue, Nov 20, 2018 at 8:06 AM Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Joseph Reeves
In reply to this post by Serkan Karakulak
Hi Serkan,

Glad I could be helpful :)

5 Coordinates because the feature is a polygon and the final coordinate duplicates the first - closing the polygon.

It might be worth looking at the Task Manager github page to see if there's any plans to present coordinates via the API. I had a very quick look at the documentation and couldn't find anything. Calling the API for the above gives me as follows:

{"taskId": 2212, "projectId": 5182, "taskStatus": "VALIDATED", "taskHistory": [{"action": "STATE_CHANGE", "actionText": "VALIDATED", "actionDate": "2018-09-27T00:47:25.252277", "actionBy": "Daniel Specht"}, {"action": "LOCKED_FOR_VALIDATION", "actionText": "00:00:55.310139", "actionDate": "2018-09-27T00:46:29.945085", "actionBy": "Daniel Specht"}, {"action": "STATE_CHANGE", "actionText": "MAPPED", "actionDate": "2018-09-19T07:12:13.214061", "actionBy": "Roger Hoorens"}, {"action": "COMMENT", "actionText": "Nothing visible", "actionDate": "2018-09-19T07:12:13.212650", "actionBy": "Roger Hoorens"}, {"action": "LOCKED_FOR_MAPPING", "actionText": "00:00:53.869298", "actionDate": "2018-09-19T07:11:19.347707", "actionBy": "Roger Hoorens"}], "perTaskInstructions": "", "isUndoable": false}

I don't know if that would be more useful to you if it contained those coordinates.

Cheers, Joseph



On Tue, 20 Nov 2018 at 16:03, Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
In reply to this post by Palolo
Oh didn't noticed that, thanks a lot!

On Tue, Nov 20, 2018 at 11:19 AM Vao Matua <[hidden email]> wrote:
Serkan,

The last value is the same as the first, it closes the polygon.

On Tue, Nov 20, 2018 at 8:06 AM Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
In reply to this post by Joseph Reeves
Thanks a lot, the geojson file seems to be more than enough for us really:) Thanks you for your help, really appreciate it.

Best,
Serkan

On Tue, Nov 20, 2018 at 11:28 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

Glad I could be helpful :)

5 Coordinates because the feature is a polygon and the final coordinate duplicates the first - closing the polygon.

It might be worth looking at the Task Manager github page to see if there's any plans to present coordinates via the API. I had a very quick look at the documentation and couldn't find anything. Calling the API for the above gives me as follows:

{"taskId": 2212, "projectId": 5182, "taskStatus": "VALIDATED", "taskHistory": [{"action": "STATE_CHANGE", "actionText": "VALIDATED", "actionDate": "2018-09-27T00:47:25.252277", "actionBy": "Daniel Specht"}, {"action": "LOCKED_FOR_VALIDATION", "actionText": "00:00:55.310139", "actionDate": "2018-09-27T00:46:29.945085", "actionBy": "Daniel Specht"}, {"action": "STATE_CHANGE", "actionText": "MAPPED", "actionDate": "2018-09-19T07:12:13.214061", "actionBy": "Roger Hoorens"}, {"action": "COMMENT", "actionText": "Nothing visible", "actionDate": "2018-09-19T07:12:13.212650", "actionBy": "Roger Hoorens"}, {"action": "LOCKED_FOR_MAPPING", "actionText": "00:00:53.869298", "actionDate": "2018-09-19T07:11:19.347707", "actionBy": "Roger Hoorens"}], "perTaskInstructions": "", "isUndoable": false}

I don't know if that would be more useful to you if it contained those coordinates.

Cheers, Joseph



On Tue, 20 Nov 2018 at 16:03, Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Michael Heißmeier-2
Hi Serkan,

just to let you know: Task squares do not have to be squares, they can have arbitrary polygon boundaries. You will find examples for these in nearly every project.

Best Regards
Michael

Serkan Karakulak, 20.11.18 17:32:
Thanks a lot, the geojson file seems to be more than enough for us really:) Thanks you for your help, really appreciate it.

Best,
Serkan

On Tue, Nov 20, 2018 at 11:28 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

Glad I could be helpful :)

5 Coordinates because the feature is a polygon and the final coordinate duplicates the first - closing the polygon.

It might be worth looking at the Task Manager github page to see if there's any plans to present coordinates via the API. I had a very quick look at the documentation and couldn't find anything. Calling the API for the above gives me as follows:

{"taskId": 2212, "projectId": 5182, "taskStatus": "VALIDATED", "taskHistory": [{"action": "STATE_CHANGE", "actionText": "VALIDATED", "actionDate": "2018-09-27T00:47:25.252277", "actionBy": "Daniel Specht"}, {"action": "LOCKED_FOR_VALIDATION", "actionText": "00:00:55.310139", "actionDate": "2018-09-27T00:46:29.945085", "actionBy": "Daniel Specht"}, {"action": "STATE_CHANGE", "actionText": "MAPPED", "actionDate": "2018-09-19T07:12:13.214061", "actionBy": "Roger Hoorens"}, {"action": "COMMENT", "actionText": "Nothing visible", "actionDate": "2018-09-19T07:12:13.212650", "actionBy": "Roger Hoorens"}, {"action": "LOCKED_FOR_MAPPING", "actionText": "00:00:53.869298", "actionDate": "2018-09-19T07:11:19.347707", "actionBy": "Roger Hoorens"}], "perTaskInstructions": "", "isUndoable": false}

I don't know if that would be more useful to you if it contained those coordinates.

Cheers, Joseph



On Tue, 20 Nov 2018 at 16:03, Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot


--
Michael
(osm:michael63)
Chairman of the HOT Training Working Group

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Serkan Karakulak
Hi Michael,

I see, thank you. We'll make sure we handle those cases correctly then. Thank you very much for pointing that out.

Best,
Serkan

On Tue, Nov 20, 2018, 11:51 AM Michael Heißmeier <[hidden email] wrote:
Hi Serkan,

just to let you know: Task squares do not have to be squares, they can have arbitrary polygon boundaries. You will find examples for these in nearly every project.

Best Regards
Michael

Serkan Karakulak, 20.11.18 17:32:
Thanks a lot, the geojson file seems to be more than enough for us really:) Thanks you for your help, really appreciate it.

Best,
Serkan

On Tue, Nov 20, 2018 at 11:28 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

Glad I could be helpful :)

5 Coordinates because the feature is a polygon and the final coordinate duplicates the first - closing the polygon.

It might be worth looking at the Task Manager github page to see if there's any plans to present coordinates via the API. I had a very quick look at the documentation and couldn't find anything. Calling the API for the above gives me as follows:

{"taskId": 2212, "projectId": 5182, "taskStatus": "VALIDATED", "taskHistory": [{"action": "STATE_CHANGE", "actionText": "VALIDATED", "actionDate": "2018-09-27T00:47:25.252277", "actionBy": "Daniel Specht"}, {"action": "LOCKED_FOR_VALIDATION", "actionText": "00:00:55.310139", "actionDate": "2018-09-27T00:46:29.945085", "actionBy": "Daniel Specht"}, {"action": "STATE_CHANGE", "actionText": "MAPPED", "actionDate": "2018-09-19T07:12:13.214061", "actionBy": "Roger Hoorens"}, {"action": "COMMENT", "actionText": "Nothing visible", "actionDate": "2018-09-19T07:12:13.212650", "actionBy": "Roger Hoorens"}, {"action": "LOCKED_FOR_MAPPING", "actionText": "00:00:53.869298", "actionDate": "2018-09-19T07:11:19.347707", "actionBy": "Roger Hoorens"}], "perTaskInstructions": "", "isUndoable": false}

I don't know if that would be more useful to you if it contained those coordinates.

Cheers, Joseph



On Tue, 20 Nov 2018 at 16:03, Serkan Karakulak <[hidden email]> wrote:
Hi Joseph,

Thanks a lot, this was exactly what we needed indeed! Much appreciated, thank you for your help.

Is there a reason that there are five coordinates for the tile btw, instead of four?

Best,



On Tue, Nov 20, 2018 at 10:10 AM Joseph Reeves <[hidden email]> wrote:
Hi Serkan,

I've not looked into this properly, but a quick look at a project on the Task Manager shows I can find a validated square:


This task 2212 appears in the project geojson, and marked as validated: https://tasks.hotosm.org/api/v1/project/5182/tasks?as_file=true

I've not double checked this is what you want, but looks like a good place to start:

"type": "MultiPolygon"}, "properties": {"taskId": 2212, "taskSplittable": true, "taskStatus": "VALIDATED", "taskX": 30348, "taskY": 34875, "taskZoom": 16}, "type": "Feature"}, {"geometry": {"coordinates": [[[[-13.2934570288688, 11.4907909783363], [-13.2879638648073, 11.4907909783363], [-13.2879638648073, 11.4961739900467], [-13.2934570288688, 11.4961739900467], [-13.2934570288688, 11.4907909783363]]]],

Cheers, Joseph

On Tue, 20 Nov 2018 at 03:47, Serkan Karakulak <[hidden email]> wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan
_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot


--
Michael
(osm:michael63)
Chairman of the HOT Training Working Group

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot
Reply | Threaded
Open this post in threaded view
|

Re: Getting the Bounding Boxes of the Validated Regions

Laurent Savaëte
In reply to this post by Serkan Karakulak

Hi Serkan,

I am in the process of extending Mapswipe (http://www.missingmaps.org/) an app that is used to create some of the task manager task geometries. Together with Benni Herfort at Heidelberg university, we're setting up a workflow to help people validate building footprints produced by ML systems. Our first target is a dataset of buildings in Tanzania that contains about 18 million footprints. The aim is to do a bit of preprocessing, to put them in a decent shape, then have volunteers validate them against satellite imagery, so that they can then be imported onto the map. Our hope is that this speeds up mapping of buildings (and possibly other elements) while also raising the resulting quality.

I think this might tie into what you're doing in 2 ways:

- our output will be a high quality dataset of validated building footprints that you could use for training

- your output could feed into the app for validation

Happy to tell you more about what we're doing in a separate discussion, if you think it's helpful.

Laurent


On 20/11/2018 03:44, Serkan Karakulak wrote:
Hi,
I am a graduate student in a Data Science program, and I wanted to get in touch with you because me and my two other friends are interested in working on a machine learning project to map areas using their satellite images and produce their labels. If we obtain a high accuracy, we thought it could be of use to the hotosm and the missingmaps initiatives.

I have first heard about Missing Maps when I came across a mapathlon event two years ago in Istanbul. We were in search for a class project for one of our courses and I remembered about the mapathlon event and we would be very happy if we could contribute to the this wonderful initiative. There are already some previous successful works on this subject, so we are very hopeful that we could come up with an algorithm with high accuracy.

In order to develop the model, we need to extract bounding boxes of the validated tiles we see at hotosm. Then we will extract the satellite images and their labels using the label-maker API which is developed by DevSeed. Is there a method to extract the coordinates of these validated tiles? 

Thank you for your time and help.

Best,

Serkan

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot

_______________________________________________
HOT mailing list
[hidden email]
https://lists.openstreetmap.org/listinfo/hot