Residential building footprints are based on the "Building" AI Layer. The Building layer is currently designed to detect roofs only. It detects any roof of a permanent structure such as a house, unit, commercial building, garage, large garden shed or carport that is designed to keep the weather out. The current definition explicitly excludes the top of a building that is designed for regular use by people, such as a rooftop basketball court or car park. If a building is partly under construction, the completed part of the roof will be detected as building.
The vectorised Building outlines exported from AI Parcels take the Roof AI Layer and perform post processing to impose regular shapes, such as straight edges and 90 degree corners. Where the building is determined to be of irregular shape, such as for round and highly complex roofs, the algorithm reverts to a natural roof contour.
Building AI Layer: Typical residential buildings, including successful capture of building under tree cover.
AI Parcel exports of Building Footprints. Note the high confidence buildings are shown with yellow fills, lower confidence buildings (such as garden sheds, and a poorly captured commercial builiding) in shades of green.
Characteristics and Recommended Use
Commercial and Industrial Buildings
The reason the pack is called "Residential Building Footprints" is that performance in commercial and industrial buildings (C&I) such as warehouses and office buildings, and CBD (downtown) is reduced compared to the excellent quality with residential buildings. Approximately 80% of C&I buildings work well, but the current generation model in the October 2019 data set finds particularly large, featureless roofs challenging. This has been resolved in an updated model, and C&I buildings will be detected with quality similar to their residential counterparts in future data sets. The tall skyscrapers and complex buildings at the heart of many cities are even more challenging (due to building lean, frequent errors and inconsistencies in parcel boundaries, and complex multi level structures where the reasonable extent of a footprint is ambiguous). CBD buildings returned with AI Parcel exports will not be usable quality in the immediate future. If you really required this kind of building data, you may find that our DSM directly will provide useful results. You can find out about exporting DSM from MapBrowser here: Exporting 3D.
The "confidence" value for each building is the best measure to determine whether the building is captured well, or whether the model was uncertain. Viewing the Building AI Layer in your area of interest can give a sense as to whether the building footprints are likely to be of good quality in an area, or direct calculations using the DSM are are better option for you.
The building footprints are particularly good at identifying corners and edges of buildings which are obscured by trees (whether or not leaves are present). The AI Layer does a good job in the majority of these situations, and enhancements in the Building Footprint vectorisation process typically improve it further. We do not capture extreme overhang, where it is difficult for a human to estimate the extent of the building under the tree.
If the level of tree overhang is of interest, the actual shapes of overhanging tree (and their areas) are available in the Residential Roof Characteristics AI Pack.
In the AI Parcel export, the "present" field denotes whether any buildings are in the parcel; any property parcel with building set to "N" indicates that it is a vacant lot. This is a good way to reliably identify vacant lots, or ones where the construction stage has not yet reached the adding of a roof. When there is an error on this flag, the incorrect cases are made up almost entirely of parcel boundary errors, where the building actually lies in the neighbouring property.
Parcel Boundary Cuts
When an AI Parcel is processed, the property parcel boundary is used to identify objects within the parcel. Objects that protrude from the parcel (due to poor parcel alignment, or changed parcel boundaries) are cut to the boundary. While this is normally the desired outcome, it can result in undesired behaviour.
Shape / Object Quality - filtering out poor building outlines through confidence scores
The "confidence" attribute is the best way to filter out cases of potentially poor quality outlines. As shown in the charts below, almost all buildings have a confidence of greater than 90% (many are in fact at 100% confidence). Depending on how you need to use the data, you may choose to discard the couple of percent of buildings with confidence lower than 90%. This is by far the easiest way to filter out the commercial/industrial buildings that respond poorly, or the other false positives that are mentioned below.
Roof classification typically include
|House roof||Shed/Outbuilding roof||Commercial roof|
|Partially obscured roof||Stadium roof|
Roof classification typically exclude
|Rooftop carpark||Awning||Mobile home|
|Shade cloth||Shipping container||Balcony/Terraces|
Confidence Distribution by Region
Please refer to Confidence for a further explanation of this value and best practices in using this score to filter the data according to your use case.