Motion-based image stitching

摘要

Systems, methods, and computer readable media for stitching or aligning multiple images (or portions of images) to generate a panoramic image are described. In general, techniques are disclosed for using motion data (captured at substantially the same time as image data) to align images rather than performing image analysis and/or registration operations. More particularly, motion data may be used to identify the rotational change between successive images. The identified rotational change, in turn, may be used to generate a transform that, when applied to an image allows it to be aligned with a previously captured image. In this way, images may be aligned in real-time using only motion data.

主权项

1. A non-transitory storage device, comprising computer code which, when executed by a computer of an image capture device, causes the computer to:
align a sequence of images by, on a paired basis:
capturing a first image of a respective image pair at the image capture device, wherein the first image has first image capture parameters;capturing first motion data for the first image;capturing a second image of the respective image pair at the image capture device, wherein the second image has second image capture parameters;capturing second motion data for the second image;deriving a single perspective transform from the first and the second image capture parameters and from a relative rotation between the first and second images indicated by the first and second motion data; andapplying the single perspective transform to a segment of the second image, wherein the perspective transform, when applied, maps points in the second image to corresponding points in the first image, in accordance with a difference in perspective of the first and the second images; andstitch the aligned segments together to form a composite image.