Image processor and image processing method

An image processing method for an image processor to detect a position of a given target of a subject shot with a camera, the image processing method comprising:

• acquiring a depth image representing, on an image plane, a distance of the subject from a camera in a depth direction as a pixel value;
• reading data of a template image prepared for the target from a memory;
• adjusting a size of the template image in accordance with a position of the template image and the distance of the subject represented by the depth image in the depth direction and evaluating the matching of the picture of the subject based on the pixel value within an area corresponding to the template image on the depth image or the image shot with the camera;
• and
• identifying the picture of the subject, the target, based on the matching evaluation result, generating position information thereof, and outputting that information, wherein:
• the step of acquiring the depth images includes acquiring depth images of a plurality of resolutions, and
• the step of adjusting the size includes evaluating the matching of the subjects in each of the depth images of one of the resolutions by restricting the evaluation to the subjects existing within a range of the distance in the depth direction associated with one of the resolutions.

A computer executing a computer program allowing the computer to detect a position of a given target of a subject shot with a camera, the computer program allowing the computer to perform:

• acquiring a depth image representing, on an image plane, distances of subjects from a camera in a depth direction as pixel values;
• reading data of a template image prepared for the target from a memory;
• adjusting a size of the template image in accordance with a position of the template image and the distance of the subject represented by the depth image in the depth direction and evaluating the matching of the picture of the subject based on the pixel value within an area corresponding to the template image on the depth image or the image shot with the camera;
• and
• identifying the picture of the subject, the target, based on the matching evaluation result, generating position information thereof, and outputting that information, wherein:
• the step of acquiring the depth images includes acquiring depth images of a plurality of resolutions, and
• the step of adjusting the size includes evaluating the matching of the subjects in each of the depth images of one of the resolutions by restricting the evaluation to the subjects existing within a range of the distance in the depth direction associated with one of the resolution.

A non-transitory, computer-readable recording media storing a computer program allowing a computer to detect a position of a given target of a subject shot with a camera, the computer program allowing the computer to perform:

• acquiring a depth image representing, on an image plane, distances of subjects from a camera in a depth direction as pixel values;
• reading data of a template image prepared for the target from a memory;
• adjusting a size of the template image in accordance with a position of the template image and the distance of the subject represented by the depth image in the depth direction and evaluating the matching of the picture of the subject based on the pixel value within an area corresponding to the template image on the depth image or the image shot with the camera;
• and
• identifying the picture of the subject, the target, based on the matching evaluation result, generating position information thereof, and outputting that information, wherein:
• the step of acquiring the depth images includes acquiring depth images of a plurality of resolutions, and
• the step of adjusting the size includes evaluating the matching of the subjects in each of the depth images of one of the resolutions by restricting the evaluation to the subjects existing within a range of the distance in the depth direction associated with one of the resolution.