System and method for producing multi-angle views of an object-of-interest from images in an image dataset
First Claim
1. A method comprising:
- receiving an image collected by a camera, wherein the image includes a plurality of pixels;
receiving distance data from a range-finding device;
registering the plurality of pixels of the image data with the distance data;
identifying, using a processor, a first location for a viewpoint;
adding a virtual object-of-interest to the image, wherein the virtual object-of-interest is added as a part of a landscape represented by the image;
identifying, using the processor, a second location for the virtual object-of-interest in the image; and
determining, using the processor, a view of the virtual object-of-interest from the first location toward the second location to test for the utility of the virtual object-of-interest to determine if it is visible from a distance and at an angle of view associated with the first location with respect to the second location.
0 Assignments
0 Petitions
Accused Products
Abstract
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.
25 Citations
20 Claims
-
1. A method comprising:
receiving an image collected by a camera, wherein the image includes a plurality of pixels;
receiving distance data from a range-finding device;
registering the plurality of pixels of the image data with the distance data;
identifying, using a processor, a first location for a viewpoint;
adding a virtual object-of-interest to the image, wherein the virtual object-of-interest is added as a part of a landscape represented by the image;
identifying, using the processor, a second location for the virtual object-of-interest in the image; and
determining, using the processor, a view of the virtual object-of-interest from the first location toward the second location to test for the utility of the virtual object-of-interest to determine if it is visible from a distance and at an angle of view associated with the first location with respect to the second location.- View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
10. An apparatus comprising:
-
a memory configured to store an image collected by a camera, wherein the image includes a plurality of pixels, and to store distance data collected by a range-finding device; and a processor configured to register the plurality of pixels of the image data with the distance data, to add a virtual object to the image at a user specified location, and to generate a view from a first location toward a second location associated with the user specified location of the virtual object, wherein the virtual object is added to as part of the scene captured in the image to test the utility of the object-of-interest by determining if the virtual object-of-interest is visible from different distances and different angles of view. - View Dependent Claims (11, 12, 13, 14)
-
-
15. A non-transitory computer-readable medium containing computer-executable instructions for performing a method comprising:
-
accessing an image collected by a camera, wherein the image includes a plurality of pixels and a virtual object added by a user within the image, the virtual object added to a street scene represented by the image; accessing distance data collected by a range-finding device; assigning three-dimensional locations to the plurality of pixels based on the distance data; identifying, using a processor, a first location for a viewpoint; identifying, using the processor, a second location for the virtual object in the image; and generating, using the processor, a modified image with the viewpoint from the first location and facing toward the second location, the modified image generated to assess the utility of the of the virtual object added in the street scene from the distance and angle of view from the first location to the second location. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification