US 11,983,887 B2
Device, computer program and method
Antonio Avitabile, Basingstoke (GB); and Salvatore Finatti, Basingstoke (GB)
Assigned to Sony Europe B.V., Weybridge (GB); and Sony Group Corporation, Tokyo (JP)
Filed by Sony Europe B.V., Weybridge (GB); and Sony Group Corporation, Tokyo (JP)
Filed on Mar. 2, 2021, as Appl. No. 17/189,928.
Claims priority of application No. 2003323 (GB), filed on Mar. 6, 2020.
Prior Publication US 2021/0279889 A1, Sep. 9, 2021
Int. Cl. G06K 9/00 (2022.01); G06N 3/02 (2006.01); G06T 3/40 (2006.01); G06T 7/20 (2017.01); G06T 9/00 (2006.01)
CPC G06T 7/20 (2013.01) [G06N 3/02 (2013.01); G06T 3/40 (2013.01); G06T 9/00 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a first image from a dynamic vision sensor and a second image from an image sensor, wherein the dynamic vision sensor and the image sensor capture at least an overlapping field of view;
determining, from the first image received from the dynamic vision sensor and the second image from the image sensor, an area of movement in the field of view of the second image from the image sensor and any differences between movement determined from the first image and second image;
applying image compression based on areas of movement in the second image from the image sensor to produce a processed image; and
outputting the processed image to a neural network based on the differences between movement in the first image and second image.