System and method for producing multi-angle views of an object-of-interest from images in an image dataset

摘要

Disclosed are a system and method for creating multi-angle views of an object-of-interest from images stored in a dataset. A user specifies the location of an object-of-interest. As the user virtually navigates through the locality represented by the image dataset, his current virtual position is determined. Using the user's virtual position and the location of the object-of-interest, images in the image dataset are selected and interpolated or stitched together, if necessary, to present to the user a view from his current virtual position looking toward the object-of-interest. The object-of-interest remains in the view no matter where the user virtually travels. From the same image dataset, another user can select a different object-of-interest and virtually navigate in a similar manner, with his own object-of-interest always in view. The object-of-interest also can be “virtual,” added by computer-animation techniques to the image dataset. For some image datasets, the user can virtually navigate through time as well as through space.

主权项

1. A method comprising:
receiving image data from an image capture device, wherein the image data includes a first photographic image and a second photographic image captured after the first photographic image; receiving distance data from a range-finding device; associating a plurality of pixels of the image data with the distance data; transforming, by a processor, the first photographic image using a portion of the image data from the second photographic image according to the received distance data; wherein the second photographic image includes a virtual object, and wherein transforming the first photographic image comprises adding the virtual object from the second photographic image to test visibility of the virtual object from a perspective of the first photographic image; and displaying the transformed image to a user to virtually navigate the image.