Information processing apparatus, information processing method, and program

A moving device control apparatus comprising:

• one or more processors;
• and
• at least one memory storing executable instructions, which when executed by the one or more processors, cause a moving device to perform a method comprising:
• acquiring a first image from a first optical system and a second image from a second optical system, the first image and the second image being acquired from an imaging apparatus that includes the first optical system and the second optical system, which are arranged in a device so that an imaging field of view of the first optical system is at least partially overlapped with an imaging field of view of the second optical system;
• performing a first stereo matching on the first and second images for a first number of feature points smaller than a number of pixels in the first image to estimate three-dimensional positions of the feature points with respect to the imaging apparatus;
• setting selectively a feature point having an estimated three-dimensional position within a three-dimensional space, defined in a moving direction of the moving device, in which an object to be detected is located, among the feature points of the first number, as a target point;
• setting surrounding points of a second number that a density of the surrounding points is higher than the feature points for which the three-dimensional positions are estimated in an image region between the target point and the feature points estimated;
• estimating, using a second stereo matching, three-dimensional positions of the set surrounding points, wherein the three-dimensional positions of the set surrounding points have not been estimated by the first stereo matching;
• and
• determining the target point is the feature point indicating a feature of an object existing in the three-dimensional space in a case where, based on a number of surrounding points for which a distance from a predetermined position of the imaging apparatus to an estimated three-dimensional position of each surrounding point is similar to a distance from the predetermined position of the imaging apparatus to the three-dimensional position of the target point, the number exceeds a threshold, and determining that the target point is noise in a case where the number of surrounding points is equal to or less than the threshold.