A. Site analysis provides a detailed map of a customisable location, providing a reliable and detailed basis for further design purposes in a multitude of industries. The provided historical data, infrastructural context and accurate climate analysis can all be instantly processed.

A. We are focusing on currency, consistency, coverage, and ease of access of aerial imagery data. Images are regularly updated covering 90% of the Australian population — with more than 100 urban areas encompassing more than 130,100 unique square km annually, and growing. Update frequency is typically six times a year for metropolitan areas, at least 3 times a year for most urban areas, and at least once a year for selected populated regional areas. Images are available on our platform within days of capture.

A. With clear vertical and industry-leading resolution of 5.5cm - 7.5cm, you can perform detailed analysis of your sites. The absolute horizontal accuracy is 19.8cm - 25.5cm, measured as root mean square of the radial distance error (RMSE) with a measurement precision of 7.5cm - 15cm within one photo. Cadastre data is currently available for NSW, VIC, QLD, and ACT. SiteAnalysis uses original data provided by our Data Sources.

A. The Site Analysis Plan is provided in the respective projected MGA Zone as indicated on the pdf and corrected for True North orientation. The geo-tif includes the coordinate reference system and the cadastre geojson is provided in WGS84 (EPSG:4326). Both files can be edited in any common GIS program (e.g., QGIS or esri ArcGIS) or inspected with online tools.

A. The site analysis product is fully automated and delivered instantly within a few minutes after ordering. Shortly after the invoice has been sent, you will receive an additional email with the download information. In case you haven't received any download notification after 10 mins, please check your spam folder (sender: service@siteanalysis.ai) or contact us directly via email.

A. To give you the opportunity to study our product before purchase, we provide you a sample of the Site Analysis product at Download Sample

A. We have put in place a mechanism for you to review and to confirm the order before payment. Unfortunately once the order is in we have the obligation to pay a third part provider for the imagery data, which we are unable to reimburse. However, we are happy to review your feedback and we are there to help you.

A. We are always looking into ways to improve our product and to offer more options including expanding the maximum size. If you currently look for a custom size please contact our service team at service@urbanfinity.com.au and we are happy to help you.

A. We provide a free sample for you to download. The sample will demonstrate the product you will receive. We hope that the sample will meet your expectations and welcome any feedback or questions you may have in regard to the accuracy and quality of our product. If you are unhappy with the image quality please send us an email to review the image data. In some instances there may be a slight variance between the cadastrial and the imagery data on the pdf. We provide in addition to the pdf, the original data as geotif, geojson, and dxf, which can be aligned using any common CAD or GIS software (not included in our service). We are here to help! If you have any questions please contact our service team at service@urbanfinity.com.au.

Theres are geosnatially referenced and can be used in geospatial programs such as ArcGIS and QGIS, these are geo-referenced shape files.

Compared to DXF files GeoJSON files can be easily imported via drag and drop to any common Geospatial program (free) and ESRI ArcGIS, and automatically overlaid with other geospatial layers. 

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. 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 are captured poorly in Gen 1, or the other false positives that are mentioned below.

Fidelity Score

gen4-lightning_bolt-1.0 introduced the fidelity score on building footprint for the first time. Where the confidence is the probability that the building identified in the location actually exists, the fidelity score measures the quality of the vectorised building footprint polygon. One of the best uses for fidelity score is to programmatically identify buildings that require a different workflow or treatment due to CBD/downtown conditions (e.g. falling back to a previous digitised outline, or flagging for manual inspection). Using a proprietary machine learning model that compares the final outline to the prediction rasters, we can accurately determine whether the polygon matches exceptionally well (1.0) or very poorly (0.0), or somewhere between.

The list below provides guidance on how to interpret a fidelity score:

• 0.9-1.0 - The vast majority of buildings have a fidelity score of 0.9 or greater, indicating an excellent match.
• 0.7-0.9 - Fidelity scores between 0.7 and 0.9 will still be good enough for many applications, but may be degraded slightly due to challenging conditions such as extensive tree overhang, shadowing or architectural complexity.
• 0.5-0.7 - Scores between 0.5 and 0.7 may be useful in situations where the shape is less critical, but should be handled with care.
• 0.0-0.5 - The lowest scoring buildings often have low confidence as well, such as a heavily shadowed garden shed with overhanging branches. If the confidence is high but the fidelity is low, it is most likely a very large, complex commercial or industrial building that exhibits very complex architecture, or extensive parallax error (building lean due to height).