System and method of aligning images

• US 8,660,383 B1
• Filed: 07/12/2012
• Issued: 02/25/2014
• Est. Priority Date: 03/14/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Callari, Francesco, Weiss-Malik, Michael
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): TORRES, JOSE
• Application Number:
  US13/547,428
• Time in Patent Office: 593 Days
• Field of Search: 382/113, 382/195, 382/276, 382/294
• US Class Current: 382/294
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: G09G 5/346 for systems having a bit-mapped display memory

Abstract

A system and method is provided for aligning images of one resolution based on both features contained in the images and the alignment of related images of a different resolution.

Claims

1. A computer-implemented method of processing geographic images having features comprising:

associating, with one or more processors, a first data structure stored in a non-transitory computer-readable medium with first geo-location data and a first set of features from a geographic image, the first set of features being associated with a geographic location;

associating, with the one or more processors, a second data structure stored in the non-transitory computer-readable medium with second geo-location data and a second set of the features, the second set of features being associated with the geographic location;

matching, with the one or more processors, a feature from the first set of features with a feature from the second set of features based on descriptor values assigned to each of the features;

determining, with the one or more processors, an alignment vector to be applied to the second geo-location data to align the matched features; and

associating, with the one or more processors, the feature in the first set of features with the second data structure dependent on the alignment vector and the geographic location of the feature.

2. The method of claim 1 wherein the data structures are associated with portions of the same geographic image.

3. The method of claim 2 wherein the geographic image is divided into tiles and the data structures correspond with the tiles.

4. The method of claim 1 further comprising a base image, wherein the alignment vector brings the first and second geo-location data into alignment with the base image.

5. The method of claim 4 wherein the alignment vector is determined based on the features and information extracted from a geographic image having a resolution different than the base image.

6. The method of claim 1 wherein a different alignment vector is applied to the first geo-location data.

7. The method of claim 6 wherein the alignment vector and different alignment vector are dependent upon weights associated with the images.