Information processing apparatus and method thereof

1. An information processing apparatus comprising:

a processor; and

a memory storing instructions that, when executed by the processor, cause the information processing apparatus to:

obtain a two-dimensional image obtained by capturing a scene including an object;

obtain parameters indicating a capturing position and capturing orientation of the two-dimensional image;

obtain a three-dimensional shape model representing a three-dimensional shape of the object;

extract three-dimensional geometrical features of the object from the three-dimensional shape model;

extract, from the two-dimensional image, two-dimensional geometrical features corresponding to the three-dimensional geometrical features;

derive a plane representing a surface of the three-dimensional shape model at a position of each of the three-dimensional geometrical features;

correct a position and an orientation of each of the three-dimensional geometrical features based on a position and an orientation of a corresponding two-dimensional geometrical feature, the capturing position and the capturing orientation of the two-dimensional image, and the plane representing the surface at the position of the three-dimensional geometrical feature; and

output a set of the three-dimensional geometrical features in which respective positions and orientations of the three-dimensional geometrical features have been corrected, as a corrected three-dimensional shape model.

2. The apparatus according to claim 1 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to extract, as the three-dimensional geometrical features, a plurality of three-dimensional sampling points representing contours of the object indicated by the three-dimensional shape model.

3. The apparatus according to claim 2 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to extract, as the two-dimensional geometrical features, a plurality of two-dimensional sampling points corresponding to the plurality of three-dimensional sampling points from an edge portion of the object captured in the two-dimensional image.

4. The apparatus according to claim 3 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to obtain a projection point by projecting each of the plurality of three-dimensional sampling points to the two-dimensional image, and extract a two-dimensional sampling point from the edge portion close to the projection point.

5. The apparatus according to claim 3 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to:

calculate correction points in the three-dimensional shape model, corresponding to the plurality of two-dimensional sampling points based on the plurality of two-dimensional sampling points, the parameters, and the calculated three-dimensional information; and

correct the three-dimensional information of the plurality of three-dimensional sampling points corresponding to the plurality of two-dimensional sampling points based on three-dimensional information of the correction points.

6. The apparatus according to claim 5 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to output a set of the plurality of three-dimensional sampling points after the correction as the three-dimensional shape model of the object.

7. The apparatus according to claim 1 , wherein the memory further stores instructions that, when executed by the processor, cause the information processing apparatus to:

calculate a line which connects a position of each of the two-dimensional geometrical features and a capturing position of the two-dimensional image; and

set, as a position of each of the three-dimensional geometrical features, an intersection of the line and the surface of the object in which the three-dimensional information is calculated.

8. An information processing method comprising:

using a processor to perform:

obtaining a two-dimensional image obtained by capturing a scene including an object;

obtaining parameters indicating capturing position and capturing orientation of the two-dimensional image;

obtaining a three-dimensional shape model representing a three-dimensional shape of the object;

extracting three-dimensional geometrical features of the object from the three-dimensional shape model;

extracting, from the two-dimensional image, two-dimensional geometrical features corresponding to the three-dimensional geometrical features;

deriving a plane representing a surface of the three-dimensional shape model at a position of each of the three-dimensional geometrical features;

correcting a position and an orientation of each of the three-dimensional geometrical features based on a position and an orientation of a corresponding two-dimensional geometrical feature, the capturing position and the capturing orientation of the two-dimensional image, and the plane representing the surface at the position of the three-dimensional geometrical feature; and

outputting a set of the three-dimensional geometrical features in which respective positions and orientations of the three-dimensional geometrical features have been corrected, as a corrected three-dimensional shape model.

9. A non-transitory computer readable medium storing a computer-executable program for causing a computer to execute an information processing method, the method comprising:

obtaining a two-dimensional image obtained by capturing a scene including an object;

obtaining parameters indicating capturing position and capturing orientation of the two-dimensional image;

obtaining a three-dimensional shape model representing a three-dimensional shape of the object;

extracting three-dimensional geometrical features of the object from the three-dimensional shape model;

extracting, from the two-dimensional image, two-dimensional geometrical features corresponding to the three-dimensional geometrical features;

deriving a plane representing a surface of the three-dimensional shape model at a position of each of the three-dimensional geometrical features;

correcting a position and an orientation of each of the three-dimensional geometrical features based on a position and an orientation of a corresponding two-dimensional geometrical feature, the capturing position and the capturing orientation of the two-dimensional image, and the plane representing the surface at the position of the three-dimensional geometrical feature; and

outputting a set of the three-dimensional geometrical features in which respective positions and orientations of the three-dimensional geometrical features have been corrected, as a corrected three-dimensional shape model.