| CPC G06T 7/73 (2017.01) [G06T 19/00 (2013.01); G06V 20/70 (2022.01); G06T 2207/30201 (2013.01); G06V 40/168 (2022.01)] | 13 Claims |
|
1. An image processing apparatus comprising:
one or more memories storing instructions; and
one or more processors executing the instructions to:
detect a feature point of an object from a plurality of images obtained by being captured from a plurality of viewpoints;
append attribute information to the detected feature point, which indicates an area of the object to which the feature point belongs; and
determine three-dimensional coordinates of a feature point to which the same attribute information is appended based on two-dimensional coordinates of the feature point in images corresponding to viewpoints not more than the plurality of viewpoints and not less than two,
wherein in the determining, for each of the same attribute information, candidate viewpoints are extracted from the plurality of viewpoints and based on the two-dimensional coordinates of the feature point on the image corresponding to a viewpoint selected from among the candidate viewpoints, the three-dimensional coordinates of the feature point to which the same attribute information is appended are determined,
in the appending, a basic model having a basic structure of the object and position information on the feature point thereof is obtained, contents of the attribute information to be appended are determined by clustering normals of the feature points identified by the position information, and the attribute information in accordance with the detected feature point is appended from the determined attribute information.
|