US 11,900,670 B2
Construction stage detection using satellite or aerial imagery
Corentin Guillo, Toulouse (FR); and Sivakumaran Somasundaram, Glasgow (GB)
Assigned to Metrostudy, Inc., Washington, DC (US)
Filed by Corentin Guillo, Toulouse (FR); and Sivakumaran Somasundaram, Glasgow (GB)
Filed on Jun. 30, 2022, as Appl. No. 17/854,280.
Prior Publication US 2024/0005656 A1, Jan. 4, 2024
Int. Cl. G06V 20/10 (2022.01); G06V 20/13 (2022.01); G06V 10/40 (2022.01); G06Q 50/08 (2012.01); G06V 10/82 (2022.01)
CPC G06V 20/176 (2022.01) [G06Q 50/08 (2013.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01); G06V 20/13 (2022.01); G06V 20/182 (2022.01)] 15 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a satellite or aerial image, or portion thereof, of a geographic area comprising one or more houses under construction as input into a machine learned model trained with a set of satellite or aerial images having houses representing a plurality of different stages of construction and corresponding labels representing such stages;
predicting which houses in the satellite or aerial image or portion thereof have completed which stages of construction by way of the machine learned model; and
sending an output from the machine learned model comprising the predictions, wherein the output comprises text comprising:
a feature name;
a label for the feature representing a prediction chosen from slab, foundation, under construction, and completed;
a decimal probability that the label for the feature is correct; and
a centroid and polygonal boundary of the feature, both expressed as geographical coordinates;
wherein the text is formatted and standardized for input into a Geographic Information System application;
wherein the different stages of construction are slab, foundation, under construction, and completed.