Road and Building Detection

analytics building detection commercial data high resolution imagery land cover mapping planetscope road detection sandbox data

Description

Globally available land cover maps derived from Planetscope imagery classifying pixels as road, building or neither. Generated on a weekly or monthly basis, Planet's Road & Building Detection can be used to stay up to date with the latest development around the globe.
By leveraging a semantic segmentation model on all the PlanetScope imagery published in a given area for a given week or month, we assign a probability value (0-255) that the pixel represents a road, building or neither object. These results are aggregated together into a weekly or monthly layer and this process is repeated through time, generating a time-series of pixel values ready for analysis.

Documentation

Planet Road and Building Detection Product Documentation

Sandbox Data

Discover samples of Road and Buiding Detection, free to all active Planet users and Sentinel Hub users with a paid subscription or a Trial account. Sandbox Data for Road and Building Detection

Resolution

4.77m at equator based on PlanetScope GSD

Geographical coverage

Global between 74° N and 60° S (seasonally dependent)

Temporal availability

01 January 2018 - present

Update Frequency

Weekly or Monthly

Band Information

NameDescriptionValues
roadsRoad Detection[0-255], (the greater the pixel value, the greater the likelihood that the pixel is classified correctly)
buildingsBuilding Detection[0-255], (the greater the pixel value, the greater the likelihood that the pixel is classified correctly)
otherNeither Roads nor Buildings[0-255], (the greater the pixel value, the greater the likelihood that the pixel is classified correctly)
alphaAlpha mask[0/255], 255 indicating valid pixels, 0 indicating invalid pixels

Custom scripts

Coming soon here

License

License

Provider

Planet

Managed By

Planet

See all datasets managed by Planet.

Contact

Sentinel Hub Forum on Planet Commmunity

Resources


Edit this collection entry on GitHub

Home