US Patent Application 17804195. TERRAIN ESTIMATION USING LOW RESOLUTION IMAGERY simplified abstract
Contents
TERRAIN ESTIMATION USING LOW RESOLUTION IMAGERY
Organization Name
Microsoft Technology Licensing, LLC==Inventor(s)==
[[Category:Roberto De Moura Estevao Filho of Teresopolis (BR)]]
[[Category:Leonardo De Oliveira Nunes of Rio de Janeiro (BR)]]
[[Category:Peder Andreas Olsen of Redmond WA (US)]]
[[Category:Anirudh Badam of Issaquah WA (US)]]
TERRAIN ESTIMATION USING LOW RESOLUTION IMAGERY - A simplified explanation of the abstract
This abstract first appeared for US patent application 17804195 titled 'TERRAIN ESTIMATION USING LOW RESOLUTION IMAGERY
Simplified Explanation
- The patent application describes a computing system that measures terrain coverage using multispectral image data. - The system generates an index array of pixels for a specific terrain, representing the relationship between reflectance values at different wavelengths. - This index array is then provided to a trained calibration model, which generates an estimated value representing the amount of terrain coverage within a geographic region. - The estimated value is outputted as the result for the specific terrain. - The calibration model is trained using reference images of training geographic regions at a higher resolution than the sample resolution.
Original Abstract Submitted
A computing system measures terrain coverage by: obtaining sample image data representing a multispectral image of a geographic region at a sample resolution; generating, based on the sample image data, an index array of pixels for a subject terrain in which each pixel has an index value that represents a predefined relationship between a first wavelength reflectance and a second wavelength reflectance; providing the index array to a trained calibration model to generate an estimated value based on the index array, the estimated value representing an estimated amount of terrain coverage within the geographic region for the subject terrain; and outputting the estimated value for the subject terrain. The trained calibration model may be trained based on training data representing one or more reference images of one or more training geographic regions containing the subject terrain at a higher resolution than the sample resolution.
