Method and apparatus for accurate localization of points of interest using a world shape
View Patent ↗Geo-referenced and oriented media items may be used to determine a location of one or more points of interest depicted by the media items. A difference between an actual capture location and orientation and a reported location and orientation may be modeled according to one or more distributions, which distribution(s) may be used to assign one or more weights to each location in the world where such weight(s) may be considered to be a likelihood that a point of interest might have been seen by a capturing device. A density map may be acquired by superimposing the derived likelihoods, and a maximum, e.g., local maximum, may be determined to represent a location of a point of interest.
1. A method comprising:
selecting, using at least one computing system, a plurality of digital media items, each media item of the plurality of digital media items having associated capture information identifying a location and orientation of a digital media device capturing the media item;
generating, using the at least one computing system, a plurality of weights for each media item of the plurality of digital media items, each weight of the media item's plurality of weights corresponding to a geographic location of a plurality of geographic locations, the weight reflects an estimated inaccuracy in the identified location and orientation of the digital media device and is generated using information including the media item's identified location and orientation, the generated weight for use in determining whether a point of interest depicted in the media item is located at the geographic location, wherein the generating of the plurality of weights is dependent on a world shape used to model the Earth; and
for each geographic location of the plurality of geographic locations, aggregating, using the at least one computing system, the plurality of weights generated for the geographic location in connection with each media item of the plurality of digital media items, an aggregated weight for a given geographic location identifying a probability that at least one point of interest is located at the given geographic location, wherein the probability is dependent on the world shape used to model the Earth.
2. The method of claim 1 , the world shape is one of an ellipsoid, sphere and plane.
3. The method of claim 1 , the generating a plurality of weights for each media item of the plurality of digital media items further comprising:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generating a capture orientation inaccuracy weight for the media item using at least one statistical orientation inaccuracy model;
generating a capture location inaccuracy weight for the media items using at least one statistical location inaccuracy model; and
generating a combined weight for the media item by combining the capture orientation and location inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
4. The method of claim 1 , each media item's orientation comprising a horizontal orientation and a vertical orientation and each media item's location comprising a horizontal location and a vertical location.
5. The method of claim 4 , the generating a plurality of weights for each media item of the plurality of digital media items further comprising:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generating a horizontal orientation capture inaccuracy weight for the media item using horizontal orientation inaccuracy statistical model;
generating a vertical orientation capture inaccuracy weight for the media item using a vertical orientation inaccuracy statistical model;
generating an orientation capture inaccuracy weight by combining the horizontal orientation capture inaccuracy weight and the vertical orientation capture inaccuracy weight;
generating a horizontal location capture inaccuracy weight for the media item using a horizontal location inaccuracy statistical model;
generating a vertical location capture inaccuracy weight for the media item using a vertical location inaccuracy statistical model;
generating a location capture inaccuracy weight by combining the horizontal location capture inaccuracy weight and the vertical location capture inaccuracy weight; and
generating a combined weight for the geographic location by combining the orientation and location capture inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
6. The method of claim 5 , the horizontal location capture inaccuracy weight is dependent on a horizontal distance between the capture location and the geographic location, the vertical location capture inaccuracy weight is dependent on a vertical distance between the capture location and the geographic location, and the horizontal and vertical distances are dependent on the world shape used to model the Earth.
7. The method of claim 5 , the horizontal orientation capture inaccuracy weight is dependent on a horizontal angle between the capture location and the geographic location, the vertical orientation capture inaccuracy weight is dependent on a vertical angle between the capture location and the geographic location, and the horizontal and vertical angles are dependent on the world shape used to model the Earth.
8. A system comprising:
at least one computing device comprising one or more processors to execute and memory to store instructions to:
select a plurality of digital media items, each media item of the plurality of digital media items having associated capture information identifying a location and orientation of a digital media device capturing the media item;
generate a plurality of weights for each media item of the plurality of digital media items, each weight of the media item's plurality of weights corresponding to a geographic location of a plurality of geographic locations, the weight reflects an estimated inaccuracy in the identified location and orientation of the digital media device and is generated using information including the media item's identified location and orientation, the generated weight for use in determining whether a point of interest depicted in the media item is located at the geographic location, wherein the generating of the plurality of weights is dependent on a world shape used to model the Earth; and
for each geographic location of the plurality of geographic locations, aggregating, use the at least one computing system, the plurality of weights generated for the geographic location in connection with each media itern of the plurality of digital media items, an aggregated weight for a given geographic location identifying a probability that at least one point of interest is located at the given geographic location, wherein the probability is dependent on the world shape used to model the Earth.
9. The system of claim 8 , the world shape is one of an ellipsoid, sphere and plane.
10. The system of claim 8 , the instructions to generate a plurality of weights for each media item of the plurality of digital media items further comprising instructions to:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generate a capture orientation inaccuracy weight for the media item using at least one statistical orientation inaccuracy model;
generate a capture location inaccuracy weight for the media items using at least one statistical location inaccuracy model; and
generate a combined weight for the media item by combining the capture orientation and location inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
11. The system of claim 8 , each media item's orientation comprising a horizontal orientation and a vertical orientation and each media item's location comprising a horizontal location and a vertical location.
12. The system of claim 11 , the instructions to generate a plurality of weights for each media item of the plurality of digital media items further comprising instructions to:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generate a horizontal orientation capture inaccuracy weight for the media item using horizontal orientation inaccuracy statistical model;
generate a vertical orientation capture inaccuracy weight for the media item using a vertical orientation inaccuracy statistical model;
generate an orientation capture inaccuracy weight by combining the horizontal orientation capture inaccuracy weight and the vertical orientation capture inaccuracy weight;
generate a horizontal location capture inaccuracy weight for the media item using a horizontal location inaccuracy statistical model;
generate a vertical location capture inaccuracy weight for the media item using a vertical location inaccuracy statistical model;
generate a location capture inaccuracy weight by combining the horizontal location capture inaccuracy weight and the vertical location capture inaccuracy weight; and
generate a combined weight for the geographic location by combining the orientation and location capture inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
13. The system of claim 12 , the horizontal location capture inaccuracy weight is dependent on a horizontal distance between the capture location and the geographic location, the vertical location capture inaccuracy weight is dependent on a vertical distance between the capture location and the geographic location, and the horizontal and vertical distances are dependent on the world shape used to model the Earth.
14. The system of claim 12 , the horizontal orientation capture inaccuracy weight is dependent on a horizontal angle between the capture location and the geographic location, the vertical orientation capture inaccuracy weight is dependent on a vertical angle between the capture location and the geographic location, and the horizontal and vertical angles are dependent on the world shape used to model the Earth.
15. A computer readable non-transitory storage medium for tangibly storing thereon computer readable instructions that when executed cause at least one processor to:
select a plurality of digital media items, each media item of the plurality of digital media items having associated capture information identifying a location and orientation of a digital media device capturing the media itern;
generate a plurality of weights for each media item of the plurality of digital media items, each weight of the media item's plurality of weights corresponding to a geographic location of a plurality of geographic locations, the weight reflects an estimated inaccuracy in the identified location and orientation of the digital media device and is generated using information including the media item's identified location and orientation, the generated weight for use in determining whether a point of interest depicted in the media item is located at the geographic location, wherein the generating of the plurality of weights is dependent on a world shape used to model the Earth; and
for each geographic location of the plurality of geographic locations, aggregating, use the at least one computing system, the plurality of weights generated for the geographic location in connection with each media item of the plurality of digital media items, an aggregated weight for a given geographic location identifying a probability that at least one point of interest is located at the given geographic location, wherein the probability is dependent on the world shape used to model the Earth.
16. The computer readable non-transitory storage medium of claim 15 , the world shape is one of an ellipsoid, sphere and plane.
17. The computer readable non-transitory storage medium of claim 15 , the instructions to generate a plurality of weights for each media item of the plurality of digital media items further comprising instructions to:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generate a capture orientation inaccuracy weight for the media item using at least one statistical orientation inaccuracy model;
generate a capture location inaccuracy weight for the media items using at least one statistical location inaccuracy model; and
generate a combined weight for the media item by combining the capture orientation and location inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
18. The computer readable non-transitory storage medium of claim 15 , each media item's orientation comprising a horizontal orientation and a vertical orientation and each media item's location comprising a horizontal location and a vertical location.
19. The computer readable non-transitory storage medium of claim 18 , the instructions to generate a plurality of weights for each media item of the plurality of digital media items further comprising instructions to:
for each geographic location of the plurality of geographic locations, the at least one computing system:
generate a horizontal orientation capture inaccuracy weight for the media item using horizontal orientation inaccuracy statistical model;
generate a vertical orientation capture inaccuracy weight for the media item using a vertical orientation inaccuracy statistical model;
generate an orientation capture inaccuracy weight by combining the horizontal orientation capture inaccuracy weight and the vertical orientation capture inaccuracy weight;
generate a horizontal location capture inaccuracy weight for the media item using a horizontal location inaccuracy statistical model;
generate a vertical location capture inaccuracy weight for the media item using a vertical location inaccuracy statistical model;
generate a location capture inaccuracy weight by combining the horizontal location capture inaccuracy weight and the vertical location capture inaccuracy weight; and
generate a combined weight for the geographic location by combining the orientation and location capture inaccuracies determined for the geographic location, the combined weight being one of the plurality of weights for a media item of the plurality of digital media items.
20. The computer readable non-transitory storage medium of claim 19 , the horizontal location capture inaccuracy weight is dependent on a horizontal distance between the capture location and the geographic location, the vertical location capture inaccuracy weight is dependent on a vertical distance between the capture location and the geographic location, and the horizontal and vertical distances are dependent on the world shape used to model the Earth.
21. The computer readable non-transitory storage medium of claim 19 , the horizontal orientation capture inaccuracy weight is dependent on a horizontal angle between the capture location and the geographic location, the vertical orientation capture inaccuracy weight is dependent on a vertical angle between the capture location and the geographic location, and the horizontal and vertical angles are dependent on the world shape used to model the Earth.