| CPC G06V 10/25 (2022.01) [G06T 7/13 (2017.01); G06T 7/62 (2017.01); G06V 10/761 (2022.01); G06T 2207/30252 (2013.01); G06V 2201/07 (2022.01)] | 19 Claims |

|
1. A method for context based separation between vehicle pixels and background pixels, the method comprises:
receiving a first image and a second image, the first image and the second images are of temporarily adjacent to each other and capture a same vehicle and background content;
obtaining a first bounding box that surrounds at least a part of the vehicle within the first image; wherein the first bounding has a first width and a first height;
obtaining a second bounding box that surrounds at least the part of the vehicle within the second image; wherein the second bounding box has a second width and a second height;
obtaining a mapping between pairs of initially matched pixels, wherein each pair comprises a first pixel and a second pixel that correspond to same entity portion, wherein the entity portion is a portion of the vehicle or of the background content;
determining, for each pair of at least some of the pairs, a first normalized relative location of a first pixel of the pair within the first bounding box and a second normalized relative location of a second pixel of the pair within the second bounding box; wherein the determining of the first normalized relative location of the first pixel is based on (a) a first axis distance from a certain vertex of the first bounding box, (b) the first width, (c) a second axis distance from the certain vertex of the first bounding box, and (d) the first height; and
determining for the each pair whether the pair is a vehicle related pair or a background content pair.
|