公开(公告)号：US12026929B2

公开(公告)日：2024-07-02

申请号：US17970514

申请日：2022-10-20

Applicant: LEICA GEOSYSTEMS AG

Inventor： Pavel Seve{hacek over (c)}ek ,  Jan Zapletal ,  Martina Bekrova

IPC: G06V10/26 ,  G06T5/77 ,  G06T7/10 ,  G06T7/194 ,  G06T7/215 ,  G06T7/50 ,  G06T7/55 ,  G06T7/70 ,  G06T15/04 ,  G06T15/60 ,  G06T17/20 ,  G06V10/764 ,  G06V20/17 ,  G06V20/70

CPC classification number: G06V10/26 ,  G06T5/77 ,  G06T7/10 ,  G06T7/194 ,  G06T7/215 ,  G06T7/50 ,  G06T7/55 ,  G06T7/70 ,  G06T15/04 ,  G06T15/60 ,  G06T17/20 ,  G06V10/764 ,  G06V20/17 ,  G06V20/70 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/10032 ,  G06T2207/20021 ,  G06V2201/07 ,  G06V2201/08

Abstract: A method for creating a texture from input images, thereby removing representations of objects from the texture, the method comprising performing semantic segmentation in a plurality of digital input images with a plurality of semantic classes, at least one of the semantic classes relating to a target object class; identifying, in at least a first input image, one or more possible instances of representations of objects belonging to the target object class, each possible instance being constituted by a plurality of contiguous instance pixels of the image pixels; determining whether the instance pixels are target pixels, target pixels being pixels constituting a representation of an object belonging to the target object class; and replacing target pixels in the texture with replacement pixels derived from one or more of the plurality of digital input images.