Microsoft Buildings vs. OpenStreetMap visualization

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

Microsoft Buildings vs. OpenStreetMap visualization

Darafei "Komяpa" Praliaskouski
Hi,

Here's a demo by azavea showing how 125 Million AI-mapped buildings relate to 33 Million buildings currently in OpenStreetMap in the same region. 

https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93  



--
Darafei Praliaskouski

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

Re: Microsoft Buildings vs. OpenStreetMap visualization

Jmapb
On 8/2/2019 7:24 AM, Darafei "Komяpa" Praliaskouski wrote:
> Here's a demo by azavea showing how 125 Million AI-mapped buildings
> relate to 33 Million buildings currently in OpenStreetMap in the same
> region.
>
> https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93

Thanks, this is interesting.

Browsing the areas I'm most familiar with in NYC (where we had a
building footprint import from city data in 2013), I find that the
buildings that are detected by Microsoft but missing from OSM are mostly
either already demolished buildings (currently mapped as
landuse=construction), small outbuildings, or simply nonexistent. In the
cemetery, Microsoft has picked out a few of the more impressive tombs
and mausoleums. And in one case Azavea seems to have failed to notice a
building that's been mapped in OSM for years (since the import.)

Browsing more rural areas in upstate NY, I see thousands of unmapped
buildings, mostly houses, that Microsoft successfully detected -- in
some cases despite tree cover. The sizes are pretty good and the
footprints are okayish. Oddly some of them seem slightly rotated, maybe
a trick of the shadows.

J


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

Re: Microsoft Buildings vs. OpenStreetMap visualization

AntiCompositeNumber
In my area, it also appears that the detection rate is fairly good. In
my brief look through I found one building where there is no building
and a few buildings that the AI did not find. The rotation issue was
fairly common as well as a general offset from the imagery (This may
be on the Mapbox side, I don't know). The footprints get the general
shape of the building mostly there, but struggle with smaller
sections. Overall, the tool seems to be good at saying "There is a
building here and it's about this big" but is less successful at
identifying the details of the buildings.

On Fri, Aug 2, 2019 at 8:17 PM Jmapb <[hidden email]> wrote:

>
> On 8/2/2019 7:24 AM, Darafei "Komяpa" Praliaskouski wrote:
> > Here's a demo by azavea showing how 125 Million AI-mapped buildings
> > relate to 33 Million buildings currently in OpenStreetMap in the same
> > region.
> >
> > https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93
>
> Thanks, this is interesting.
>
> Browsing the areas I'm most familiar with in NYC (where we had a
> building footprint import from city data in 2013), I find that the
> buildings that are detected by Microsoft but missing from OSM are mostly
> either already demolished buildings (currently mapped as
> landuse=construction), small outbuildings, or simply nonexistent. In the
> cemetery, Microsoft has picked out a few of the more impressive tombs
> and mausoleums. And in one case Azavea seems to have failed to notice a
> building that's been mapped in OSM for years (since the import.)
>
> Browsing more rural areas in upstate NY, I see thousands of unmapped
> buildings, mostly houses, that Microsoft successfully detected -- in
> some cases despite tree cover. The sizes are pretty good and the
> footprints are okayish. Oddly some of them seem slightly rotated, maybe
> a trick of the shadows.
>
> J
>
>
> _______________________________________________
> talk mailing list
> [hidden email]
> https://lists.openstreetmap.org/listinfo/talk

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

Re: Microsoft Buildings vs. OpenStreetMap visualization

General Discussion mailing list
While you observe quality problems with imports,  you can contribute to better document these problems  with samples of buildings ( list of osm_id  and brief description of observations ).
 
Pierre


Le vendredi 2 août 2019 23 h 34 min 17 s UTC−4, AntiCompositeNumber <[hidden email]> a écrit :


In my area, it also appears that the detection rate is fairly good. In
my brief look through I found one building where there is no building
and a few buildings that the AI did not find. The rotation issue was
fairly common as well as a general offset from the imagery (This may
be on the Mapbox side, I don't know). The footprints get the general
shape of the building mostly there, but struggle with smaller
sections. Overall, the tool seems to be good at saying "There is a
building here and it's about this big" but is less successful at
identifying the details of the buildings.

On Fri, Aug 2, 2019 at 8:17 PM Jmapb <[hidden email]> wrote:

>
> On 8/2/2019 7:24 AM, Darafei "Komяpa" Praliaskouski wrote:
> > Here's a demo by azavea showing how 125 Million AI-mapped buildings
> > relate to 33 Million buildings currently in OpenStreetMap in the same
> > region.
> >
> > https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93
>
> Thanks, this is interesting.
>
> Browsing the areas I'm most familiar with in NYC (where we had a
> building footprint import from city data in 2013), I find that the
> buildings that are detected by Microsoft but missing from OSM are mostly
> either already demolished buildings (currently mapped as
> landuse=construction), small outbuildings, or simply nonexistent. In the
> cemetery, Microsoft has picked out a few of the more impressive tombs
> and mausoleums. And in one case Azavea seems to have failed to notice a
> building that's been mapped in OSM for years (since the import.)
>
> Browsing more rural areas in upstate NY, I see thousands of unmapped
> buildings, mostly houses, that Microsoft successfully detected -- in
> some cases despite tree cover. The sizes are pretty good and the
> footprints are okayish. Oddly some of them seem slightly rotated, maybe
> a trick of the shadows.
>
> J
>
>
> _______________________________________________
> talk mailing list
> [hidden email]
> https://lists.openstreetmap.org/listinfo/talk

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

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

Re: Microsoft Buildings vs. OpenStreetMap visualization

General Discussion mailing list
In reply to this post by Darafei "Komяpa" Praliaskouski
Hi

Is the 'Bing only' vector? 

On 02/08/2019 12:24, Darafei "Komяpa" Praliaskouski wrote:
Hi,

Here's a demo by azavea showing how 125 Million AI-mapped buildings relate
to 33 Million buildings currently in OpenStreetMap in the same region.

https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93





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


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

Re: Microsoft Buildings vs. OpenStreetMap visualization

General Discussion mailing list
As far as I know, the "Bing Only" layer in the comparison tool represents the vector data that Microsoft has made available here: https://github.com/Microsoft/USBuildingFootprints

My experience has been that about 50% of the Bing buildings are rotated to an incorrect orientation. In other rare cases it mapped the various puddles on a flat roof as separate buildings. So I personally would not use the Bing data as it is too inaccurate.

As far as the comparison tool - it looks great! But I did notice that it failed to recognize buildings that exist in OSM as multipolygon relations. I already sent feedback to the tool developer about this.

-Rassilon

On 8/5/2019 8:58 AM, Dave F via talk wrote:
Hi

Is the 'Bing only' vector???

On 02/08/2019 12:24, Darafei "Kom??pa" Praliaskouski wrote:
Hi,

Here's a demo by azavea showing how 125 Million AI-mapped buildings relate
to 33 Million buildings currently in OpenStreetMap in the same region.

https://demos.azavea.com/building-footprint-comparison/#4.4/38.67/-93.93





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


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



Virus-free. www.avast.com

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