Utility pole geotagger

• US 8,818,031 B1
• Filed: 03/02/2012
• Issued: 08/26/2014
• Est. Priority Date: 03/02/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kelly, James Fintan, Wang, Matthew, Skinner, Michael, Perry, Alexander Robert, Hendrickson, John
• Primary Examiner(s): Cunningham, Gregory F
• Application Number:
  US13/410,657
• Time in Patent Office: 907 Days
• Field of Search: 356/3.1, 356/623, 382/103, 701/489, 701/512
• US Class Current: 382/103
• CPC Class Codes: G06V 20/20 in augmented reality scenes

Abstract

According to one aspect, embodiments of the invention provide a method for determining the geographic location of an object, the method comprising retrieving at a vision system a plurality of images from a database, each image related to a respective vantage point, detecting, with the vision system, the object in at least two of the plurality of images, generating a vector in relation to the respective vantage point for each image in which the object was detected, and triangulating, based on the intersection of at least two vectors, the geographic location of the object.

Claims

1. A method for determining the geographic location of an object, the method comprising:

retrieving, by one or more processors, a plurality of images from a database, each image related to a respective vantage point;

analyzing, by the one or more processors, each image to determine if the object is present in the image;

detecting, by the one or more processors, the object in at least two of the plurality of images;

generating, by the one or more processors, a vector in relation to the respective vantage point for each image in which the object was detected; and

triangulating, based on the intersection of at least two vectors, the geographic location of the object.

2. The method of claim 1, further comprising combining, in a single representation, vectors from each image in which the object was detected.

3. The method of claim 1, further comprising outputting to an interface a representation of the geographic location of the object.

4. The method of claim 1, further comprising filtering the geographic location of the object.

5. The method of claim 4, wherein filtering the geographic location of the object comprises:

clustering intersections of vectors into groups based on proximity;

identifying a first group of vectors containing the highest number of intersections;

disregarding vectors included within the first group;

identifying, in response to disregarding, a second group of vectors which no longer contains intersections; and

eliminating, in response to identifying, vectors included within the second group.

6. The method of claim 4, wherein filtering the geographic location of the object comprises confirming the presence of the object in reference to aerial or satellite imagery.

7. The method of claim 4, wherein filtering the geographic location of the object comprises confirming the presence of the object in reference to point cloud data of the geographic location.

8. The method of claim 1, wherein generating a vector comprises:

calculating a horizontal position for each image in which the object was detected;

associating each horizontal position with a rotational angle in relation to the respective vantage point of the related image.

9. The method of claim 1, wherein the one or more processors are configured to:

break down each image into a plurality of pixels; and

individually analyze each pixel for a structure representative of the object.

10. The method of claim 9, wherein individually analyzing comprises:

applying a single line detector to each one of the plurality of pixels at a plurality of different orientations; and

recording each pixel'"'"'s response to the line detector at each one of the plurality of different orientations.

11. The method of claim 10, further comprising encoding each pixel with a color indicative of whether the pixels response to the line detector signifies the presence of the structure representative of the object.

12. The method of claim 11, wherein calculating the horizontal position comprises:

filtering the encoded pixels to identify a grouping of pixels indicative of the presence of the structure representative of the object; and

calculating an average horizontal position of the grouping of pixels.

13. A system for determining the geographic location of an object, the system comprising:

an interface configured to receive a defined geographic area from a user;

a database configured to store a plurality of images in relation to the defined geographic area;

a vision system configured to receive the plurality of images from the database, analyze each image to determine if the object is present in the image, and identify the presence of the object within at least two of the plurality of images; and

a processor configured to generate a vector for each image in which the object was detected and triangulate, based on the intersection of at least two vectors, the geographic location of the object.

14. The system of claim 13, further comprising an output display configured to provide the geographic location of the object to the user.

15. The system of claim 13, wherein the vision system comprises:

a single line detector; and

an encoder,

wherein the vision system is configured to break down each one of the plurality of images into a plurality of pixels and apply the single line detector to each one of the plurality of pixels at a plurality of different orientations, and

wherein the encoder is configured to encode each pixel with a color indicative of whether the pixels response to the line detector signifies the presence of a structure representative of the object.

16. The system of claim 13, wherein in generating the vector for each image, the processor is further configured to calculate a horizontal position for each image in which the object was detected, associate each horizontal position with a rotational angle in reference to the related image.

17. A non-transitory computer readable medium comprising computer-executable instructions that when executed on a processor performs a method for determining the geographic location of an object, the method comprising acts of:

retrieving at a vision system a plurality of images from a database, each image related to a respective vantage point;

analyzing, with the vision system, each image to determine if the object is present in the image;

detecting, with the vision system, the object in at least two of the plurality of images;

generating a vector in relation to the respective vantage point for each image in which the object was detected; and

triangulating, based on the intersection of at least two vectors, the geographic location of the object.

18. The computer readable medium according to claim 17, wherein generating a vector comprises:

calculating a horizontal position for each image in which the object was detected;

associating each horizontal position with a rotational angle in relation to the respective vantage point of the related image.

19. The computer readable medium according to claim 17, wherein the vision system is configured to:

break down each image into a plurality of pixels;

apply a single line detector to each one of the plurality of pixels at a plurality of different orientations; and

record each pixel'"'"'s response to the line detector at each one of the plurality of different orientations.

20. The computer readable medium according to claim 19, wherein the method further comprises encoding each pixel with a representation indicative of whether the pixels response to the line detector signifies the presence of a structure representative of the object.