Information processing apparatus, information processing method, and storage medium

An information processing method comprising:

• generating a map element that is based on a position and orientation of an image capturing apparatus estimated from an image obtained by performing image capturing of an environment with the image capturing apparatus being mounted on a moving body and three-dimensional position information in the environment about a feature point included in the image;
• generating three-dimensional map information based on a plurality of map elements, each corresponding to the map element, generated from images having a difference in point of view captured by the image capturing apparatus at a plurality of different positions and orientations;
• correcting, in such a way as to make smaller a reprojection error of a common feature point included in common in a first map element group out of the three-dimensional map information, at least one of a position and orientation of the image capturing apparatus and three-dimensional position information about the feature point included in the first map element group;
• and
• correcting, in such a way as to make smaller a reprojection error of the common feature point with use of a second map element group in which a wider difference in point of view is obtained than in the first map element group with respect to the common feature point in a case where a difference in point of view of images including the common feature point is less than or equal to a predetermined value, at least one of a position and orientation of the image capturing apparatus and three-dimensional position information about the feature point included in the second map element group.

A non-transitory computer-readable storage medium storing computer-executable instructions that, when executed by a computer, cause the computer to perform an information processing method comprising:

• generating a map element that is based on a position and orientation of an image capturing apparatus estimated from an image obtained by performing image capturing of an environment with the image capturing apparatus being mounted on a moving body and three-dimensional position information in the environment about a feature point included in the image;
• generating three-dimensional map information based on a plurality of map elements, each corresponding to the map element, generated from images having a difference in point of view captured by the image capturing apparatus at a plurality of different positions and orientations;
• correcting, in such a way as to make smaller a reprojection error of a common feature point included in common in a first map element group out of the three-dimensional map information, at least one of a position and orientation of the image capturing apparatus group and three-dimensional position information about the feature point included in the first map element;
• and
• correcting, in such a way as to make smaller a reprojection error of the common feature point with use of a second map element group in which a wider difference in point of view is obtained than in the first map element group with respect to the common feature point in a case where a difference in point of view of images including the common feature point is less than or equal to a predetermined value, at least one of a position and orientation of the image capturing apparatus and three-dimensional position information about the feature point included in the second map element group.