Method and apparatus for accurate localization of points of interest
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 a computing device, a plurality of digital media items, each digital media item of the plurality having associated capture information identifying a location and orientation of a digital media device capturing the digital media item;
generating, using the computing device, a plurality of weights for each digital media item in the plurality, each weight of the digital 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 digital media item's identified location and orientation, the weight for use in determining whether a point of interest depicted in the digital media item is located at the geographic location;
aggregating, using the computing device, the plurality of weights generated for the geographic location in connection with each digital 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; and
generating, using the computing device, a density map comprising a plurality of points, each geographic location of the plurality corresponding to a point of the plurality of points of the density map, the density map generation comprising associating the aggregated weight of a geographic location of the plurality to the point of the plurality of points corresponding to the geographic location.
2. The method of claim 1 , the digital media item selection further comprising:
selecting, using the computing device, the plurality of digital media items using metadata associated with each digital media item of the plurality, the associated metadata identifying a specific point of interest.
3. The method of claim 2 , the geographic location of the specific point of interest corresponding to the point of the plurality of points of the density map having a corresponding density that is a threshold maximum density.
4. The method of claim 1 , the information used in generating the weight corresponding to a geographic location including the digital media item's identified location and orientation and further comprising altitude and inclination information associated with the digital media item.
5. The method of claim 1 , the information used in generating the weight corresponding to a geographic location including the digital media item's identified location and orientation and further comprising altitude, inclination and focus distance information associated with the digital media item.
6. The method of claim 1 , the digital media item selection further comprising:
analyzing, using the computing device, a digital media item of the plurality to detect an object depicted in the digital media item; and
removing, using the computing device, the digital media item from the plurality of digital media items where the object is detected in the digital media item.
7. The method of claim 6 , the detected object comprises a face.
8. The method of claim 6 , the detected object comprises a non-stationary object.
9. The method of claim 1 , the generation of the plurality of weights for a digital media item of the plurality further comprising:
generating, using the computing device, a weight of the digital media item's plurality of weights corresponding to a geographic location of a plurality of geographic locations using at least one statistical model.
10. The method of claim 9 , the at least one statistical model comprising a Gaussian distribution.
11. The method of claim 9 , the at least one statistical model comprising a Gamma distribution.
12. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor associated with a computing device, performs a method comprising:
selecting a plurality of digital media items, each digital media item of the plurality having associated capture information identifying a location and orientation of a digital media device capturing the digital media item;
generating a plurality of weights for each digital media item in the plurality, each weight of the digital 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 digital media item's identified location and orientation, the weight for use in determining whether a point of interest depicted in the digital media item is located at the geographic location;
aggregating the plurality of weights generated for the geographic location in connection with each digital 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; and
generating a density map comprising a plurality of points, each geographic location of the plurality corresponding to a point of the plurality of points of the density map, the density map generation comprising associating the aggregated weight of a geographic location of the plurality to the point of the plurality of points corresponding to the geographic location.
13. The non-transitory computer-readable storage medium of claim 12 , the digital media item selection further comprising:
selecting the plurality of digital media items using metadata associated with each digital media item of the plurality, the associated metadata identifying a specific point of interest.
14. The non-transitory computer-readable storage medium of claim 13 , the geographic location of the specific point of interest corresponding to the point of the plurality of points of the density map having a corresponding density that is a threshold maximum density.
15. The non-transitory computer-readable storage medium of claim 12 , the information used in generating the weight corresponding to a geographic location including the digital media item's identified location and orientation and further comprising altitude and inclination information associated with the digital media item.
16. The non-transitory computer-readable storage medium of claim 12 , the information used in generating the weight corresponding to a geographic location including the digital media item's identified location and orientation and further comprising altitude, inclination and focus distance information associated with the digital media item.
17. The non-transitory computer-readable storage medium of claim 12 , the digital media item selection further comprising:
analyzing, using the computing device, a digital media item of the plurality to detect an object depicted in the digital media item; and
removing, using the computing device, the digital media item from the plurality of digital media items where the object is detected in the digital media item.
18. The non-transitory computer-readable storage medium of claim 17 , the detected object comprises a non-stationary object.
19. The non-transitory computer-readable storage medium of claim 12 , the generation of the plurality of weights for a digital media item of the plurality further comprising:
generating, using the computing device, a weight of the digital media item's plurality of weights corresponding to a geographic location of a plurality of geographic locations using at least one statistical model.
20. A computing device comprising:
a processor;
a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
selecting logic executed by the processor for selecting a plurality of digital media items, each digital media item of the plurality having associated capture information identifying a location and orientation of a digital media device capturing the digital media item;
generating logic executed by the processor for generating a plurality of weights for each digital media item in the plurality, each weight of the digital 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 digital media item's identified location and orientation, the weight for use in determining whether a point of interest depicted in the digital media item is located at the geographic location;
aggregating logic executed by the processor for aggregating the plurality of weights generated for the geographic location in connection with each digital 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; and
generating logic executed by the processor for generating a density map comprising a plurality of points, each geographic location of the plurality corresponding to a point of the plurality of points of the density map, the density map generation comprising associating the aggregated weight of a geographic location of the plurality to the point of the plurality of points corresponding to the geographic location.