Product catalogue

TensorFlight provides high-quality data on commercial properties generated from images using state-of-the-art AI. Using different imagery sources from different perspectives (satellite, aerial, drone and street view) we are able to extract reliable data. 

Current capabilities of TensorFlight

Customization and other items

How TensorFlight will deliver results data to me?   

Output data types

Current capabilities


Object type
Output type
Commercial building footprintPolygonFootprint of commercial or industrial building - e.g. shopping mall or gas station.
Residential building footprintPolygonFootprint of residential building - either house or block of flats.
Temporary building footprintPolygon Building-like structure that is not permanent - e.g. tent or trailer.
Missing part of buildingPolygonPart of the building that is missing a standard structure - e.g. it is still in construction or part of the roof that have been torn by a Hurricane
Building degradationPolygonProperty degradation that is not affecting a structural integrity of the property - e.g. pooling water, missing shingles, facade paint cracking.
TreeBounding boxTree - posing risk of catching fire or falling under heavy wind.
Dead treeBounding boxDead tree is likely dead, so it's posing higher risk of fire and wind than tree with leaves.
VehicleBounding boxVehicle - e.g. car, truck or ship
Parking spaceBounding boxParking space - counting empty parking spots helps estimate activity around the property.
Solar panelsPolygonGroup of solar panels. If multiple solar panels are adjacent they are counted as a one group.
Wind-borne debris Bounding boxItems nearby property that can be blown by the wind and damage the property envelope - e.g. chairs, lumber, piles of trash.
Mechanical euipment on the roofBounding boxMechanical equipment on the roof, that can be blown by the wind - e.g. HVAC.
PoolPolygonSwimming pool. Other water sources like ponds or fountains are not included
Window or skylightPolygonEither skylight on the roof or window on the facade.
Antenna or satellite dishesBounding boxAntennas or satellite dishes on the roof that can be blown by the wind.
Construction typeClassificationClassification of construction type - e.g. wood frame, masonry, tilt-up, engineered structure
Number of storiesClassificiationCount of stories in the building.
Occupancy typeClassifitcationType of building usage - e.g. Retail trade, Professional technical and business, Apartment/Condo, Restaurants.
SignageBounding boxA sign that allows to extract more information about the business or pose a risk of blowing by the wind.
Door or gatePolygonDoor, if visible from imagery.
Building heightRegressionHeight of building in meters.
Estimated building ageRegressionEstimate building age based on the visual characteristics.
Roof shapeClassificiationFlat, low/moderate/steep pitch.
Roof materialClassificationE.g. metal, shingle, tile.
Roof ageRegressionTime since roof was remodeled last time.

Customization and other items

For client needs we also prepare individual projects that consist of:

  • Improving accuracy of existing classes. We usually can reach 90%+ accuracy of direct work on a specific class in 2-8 weeks given priorities specified by the client.
  • New object types. We can add also add new object classes upon request. It usually takes between 1 and 3 months to support a new object class.

How TensorFlight will deliver data results to me?

  • Web dashboard: Web dashboard that allows users to request new processing or view and edit results of our analyses. Please create an account and explore the dashboard at .
  • GeoJSON: Standard format for describing GIS polygons easily integrated with web mapping tools available via the API accessible via an API.
  • Shapefile: Shapefile is one of standard GIS formats that can be easily imported into tools like ArcGIS or QGIS available via the API of the dashboard.
  • Vector tiles: URLs to slippy map tiles with vectors that can be overlaid on top of web based mapping tools available via the API. Example tile.

Output type

Bounding box

Rectangle around the object – min/max latitude/longitude.

Using this output type you can estimate object dimensions – e.g. bigger HVAC or bigger trees pose higher risk in case of a heavy wind. Based on object location we can also understand magnitude of the risk – e.g. tree or wind-borne debris dangerously close to the property is more likely to cause damage.

  1. Example


List of latitude/longitude points wrapping around the object.

This allows us to compute detailed square footage of the object. For example, using this data we can compute square footage of the property or percentage of the roof covered by solar panels or glass.

  1. Example