	US 12,107,639 B2
	System of morphology recognition for optimizing RF propagation model
Miroslav Budic, Murphy, TX (US); Yimin Nie, Saint-Laurent (CA); Aydin Sarraf, Saint-Laurent (CA); and Taesuh Park, Santa Clara, CA (US)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Appl. No. 17/754,208
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Oct. 16, 2020, PCT No. PCT/IB2020/059738 § 371(c)(1), (2) Date Mar. 25, 2022, PCT Pub. No. WO2021/074868, PCT Pub. Date Apr. 22, 2021.
Claims priority of provisional application 62/923,266, filed on Oct. 18, 2019.
Prior Publication US 2022/0329331 A1, Oct. 13, 2022
Int. Cl. H04B 17/391 (2015.01); H04B 17/373 (2015.01)

CPC H04B 17/3913 (2015.01) [H04B 17/373 (2015.01)]

16 Claims

1. A method for determining a Radio Frequency (RF) propagation model for a coverage area from an image view of the coverage area, the method comprising:

selecting the coverage area for a transmission point of a transmitter;

obtaining the image view of the selected coverage area;

quantifying, using a machine learning model, obstacles to RF propagation from the obtained image view based on obstacle types and obstacle density parameters for each obstacle type to generate a confidence score for selected combinations of obstacle types and obstacle density parameters to determine a morphology type, from a plurality of morphology types, for the selected coverage area; and

determining the RF propagation model for the selected coverage area based on the morphology type.