Name: BuildingFootprints

Display Field: OBJECTID

Type: Feature Layer

Geometry Type: esriGeometryPolygon

Description: <DIV STYLE="text-align:Left;"><DIV><P><SPAN>Microsoft says the building extraction was done in two stages:</SPAN><SPAN>1.Semantic Segmentation – Recognizing building pixels on the aerial image using DNNs</SPAN><SPAN>2.Polygonization – Converting building pixel blobs into polygons</SPAN></P><P><SPAN>We developed a method that approximates the prediction pixels into polygons making decisions based on the whole prediction feature space. This is very different from standard approaches, e.g. Douglas-Peucker algorithm, which are greedy in nature. The method tries to impose some of a priory building properties, which are, at the moment, manually defined and automatically tuned. Some of these a priori properties are:</SPAN></P><P><SPAN>1.The building edge must be of at least some length, both relative and absolute, e.g. 3 meters</SPAN><SPAN>2.Consecutive edge angles are likely to be 90 degrees</SPAN><SPAN>3.Consecutive angles cannot be very sharp, smaller by some auto-tuned threshold, e.g. 30 degrees</SPAN><SPAN>4.Building angles likely have very few dominant angles, meaning all building edges are forming angle of (dominant angle ± nπ/2)</SPAN></P><P><SPAN>In near future, we will be looking to deduce this automatically from existing building information. </SPAN><SPAN>We track various metrics to measure the quality of the output. Estimated building matching metrics:</SPAN><SPAN>Precision 99.3% </SPAN><SPAN>Recall 93.5% </SPAN><SPAN>Our metrics show that in the vast majority of cases the quality is at least as good as data hand digitized buildings in OpenStreetMap. It is not perfect, particularly in dense urban areas but it is still awesome.</SPAN></P><P><SPAN /></P></DIV></DIV>

Copyright Text: Credit given to Microsoft and Flathead County GIS would be appreciated when deriving products from this data.

Default Visibility: true

MaxRecordCount: 1000

Supported Query Formats: JSON, geoJSON, PBF

Min Scale: 10000

Max Scale: 0

Supports Advanced Queries: false

Supports Statistics: false

Has Labels: false

Can Modify Layer: false

Can Scale Symbols: false

Supports Datum Transformation: true

Extent:

XMin: -1.281434509109149E7
YMin: 6034603.591255204
XMax: -1.2576092669845589E7
YMax: 6283562.225382589
Spatial Reference: 102100  (3857)

Drawing Info:

Renderer:
Simple Renderer:
Symbol:
Style: esriSFSSolid
Color: [214, 214, 214, 255]
Outline:
Style: esriSLSSolid
Color: [178, 178, 178, 255]
Width: 0
Label: N/A
Description: N/A
Transparency: 15
Labeling Info:

Advanced Query Capabilities:

Supports Statistics: false
Supports OrderBy: false
Supports Distinct: false
Supports Pagination: false
Supports TrueCurve: true
Supports Returning Query Extent: true
Supports Query With Distance: true
Supports Sql Expression: false
Supports Query With ResultType: false
Supports Returning Geometry Centroid: false

HasZ: false

HasM: false

Has Attachments: false

HTML Popup Type: esriServerHTMLPopupTypeAsHTMLText

Type ID Field: null

Fields:

• Shape ( type: esriFieldTypeGeometry, alias: Shape )
• OBJECTID ( type: esriFieldTypeInteger, alias: OBJECTID )
• FID_1 ( type: esriFieldTypeDouble, alias: FID_1 )
• Shape_STAr ( type: esriFieldTypeDouble, alias: Shape_STAr )
• Shape_STLe ( type: esriFieldTypeDouble, alias: Shape_STLe )
• FID ( type: esriFieldTypeOID, alias: FID )

Supported Operations:   Generate Renderer   Return Updates

  Iteminfo   Thumbnail   Metadata