Stereoscopic image aligning apparatus, stereoscopic image aligning method, and program of the same

摘要

A stereoscopic image aligning apparatus (200) automatically aligns image pairs for stereoscopic viewing in a shorter amount of time than conventional apparatuses, which is applicable to image pairs captured by a single sensor camera or a variable baseline camera, without relying on camera parameters. The stereoscopic image aligning apparatus (200) includes: an image pair obtaining unit (205) obtaining an image pair including a left-eye image and a right-eye image corresponding to the left-eye image; a corresponding point detecting unit (252) detecting a corresponding point representing a set of a first point included in a first image that is one of the images of the image pair and a second point included in a second image that is the other of the images of the image pair and corresponding to the first point; a first matrix computing unit (254) computing a homography transformation matrix for transforming the first point such that a vertical parallax between the first and second points is smallest and an epipolar constraint is satisfied; a transforming unit (260) transforming the first image using the homography transformation matrix; and an output unit (210) outputting: a third image that is the transformed first image; and the second image.

主权项

1. A stereoscopic image aligning apparatus, comprising:
an image pair obtaining unit configured to obtain an image pair including a left-eye image and a right-eye image that corresponds to the left-eye image; a corresponding point detecting unit configured to detect a corresponding point that represents a set of a first point and a second point, the first point being included in a first image that is one of the images of the image pair, and the second point being included in a second image that is the other of the images of the image pair and corresponding to the first point; a first matrix computing unit configured to compute a homography transformation matrix for transforming the first point such that a vertical parallax between the first point and the second point is smallest and an epipolar constraint is satisfied; a transforming unit configured to transform the first image using the homography transformation matrix; and an output unit configured to output a third image and the second image, the third image being the transformed first image.