US 12,250,385 B2
Foveated partial image compression using automatically detected landmarks
Jacob Gorm Hansen, Ryomgård (DK)
Assigned to Vertigo.ai ApS, Ryomgård (DK)
Filed by Vertigo.ai ApS, Ryomgård (DK)
Filed on Dec. 9, 2022, as Appl. No. 18/078,179.
Claims priority of provisional application 63/288,955, filed on Dec. 13, 2021.
Prior Publication US 2023/0188731 A1, Jun. 15, 2023
Int. Cl. H04N 19/167 (2014.01); G06T 3/4046 (2024.01); G06T 3/4084 (2024.01); G06T 7/246 (2017.01); G06T 7/73 (2017.01); H04N 19/105 (2014.01); H04N 19/12 (2014.01); H04N 19/132 (2014.01); H04N 19/172 (2014.01); H04N 19/42 (2014.01); H04N 19/60 (2014.01); H04N 19/85 (2014.01)
CPC H04N 19/167 (2014.11) [G06T 3/4046 (2013.01); G06T 3/4084 (2013.01); G06T 7/248 (2017.01); G06T 7/74 (2017.01); H04N 19/105 (2014.11); H04N 19/12 (2014.11); H04N 19/132 (2014.11); H04N 19/172 (2014.11); H04N 19/42 (2014.11); H04N 19/60 (2014.11); H04N 19/85 (2014.11); G06T 2207/10016 (2013.01); G06T 2207/30201 (2013.01)] 10 Claims
OG exemplary drawing
 
1. An image transmission method comprising:
inputting a pre-processed image;
automatically localizing at least one primary feature in the pre-processed image;
automatically determining a position within the pre-processed image of at least one landmark corresponding to the at least one primary feature;
automatically foveating the pre-processed image to emphasize portions of the pre-processed image within a pre-determined measure of closeness to the landmark(s); and
transmitting the foveated image to at least one recipient system, said recipient system reconstructing a received version of the pre-processed image by inverse foveation;
selecting numerical weights for each landmark;
adjusting the displacement according to an incompressible fluid flow model with the numerical weights applied as corresponding pressures at each landmark, said recipient system reconstructing the received version of the pre-processed image by computing an inverse of the fluid flow model;
in which;
the pre-processed image is one of a series of video image frames; and
the step of automatically foveating the pre-processed image comprises increasing a spatial sampling rate around the landmarks of interest.